#platformcapitalism — Public Fediverse posts

Fear and Loathing of AI (Part III): “Learn AI” Is the New “Learn to Code”

By Cliff Potts, CSO, and Editor-in-Chief of WPS News

There is a sentence that shows up in every technological cycle right before the disappointment phase begins.

“Just learn the skill.”

It sounds empowering. It sounds reasonable. It sounds like personal agency.

It is also a lie we have been telling people for decades.

The obedience script

“Learn to code” was never about opportunity.
It was about discipline.

It trained people to accept that:

• structural failures are personal problems,
• economic insecurity is an individual moral test,
• and survival depends on constant retraining at your own expense.

When the promised jobs didn’t materialize—or paid far less than advertised—the story shifted seamlessly: you didn’t learn the right language, the right framework, the right stack.

Now the phrase has been updated.

“Learn AI.”

Same script. Same pressure. Same outcome.

Skills don’t collapse — markets do

Coding did not fail because people were lazy or incapable. It failed because markets flooded, tools commoditized, and labor lost leverage.

AI will follow the same arc, only faster.

The moment a skill becomes:

• widely accessible,
• easily automated,
• and expected rather than rewarded,

it stops being a path to security and becomes a baseline requirement for staying afloat.

The reward for compliance is not prosperity.
It is continued participation.

Training as cost transfer

Here is what “learn AI” really means in practice:

• You pay for the courses.
• You absorb the time cost.
• You shoulder the career risk.
• You adapt repeatedly as tools change.
• You accept lower pay because “AI makes you more efficient.”

None of that is accidental.

It is a system designed to push costs downward while extracting value upward.

The more often you are told to retrain, the clearer it becomes that training itself is the product.

The illusion of agency

People are encouraged to believe that mastery equals control.

But control does not come from skill alone.
It comes from:

• ownership,
• bargaining power,
• regulation,
• and collective leverage.

Without those, skill is just labor dressed up as self-improvement.

Learning AI may help you keep your job a little longer.
It will not protect you from the logic of the system deploying it.

What learning actually means now

This does not mean you should refuse to learn.

It means you should learn without illusions.

Learn AI the way you learn any tool:

• to reduce friction,
• to save time,
• to extend what you already do.

Do not learn it expecting salvation.
Do not learn it expecting loyalty from platforms.
Do not learn it expecting the market to reward you for effort.

Markets reward leverage, not diligence.

The quiet truth

The most dangerous part of “learn AI” is not that it is false.

It is that it is incomplete.

It tells people how to adapt, but never who benefits.
It demands flexibility, but never offers stability.
It promises relevance, but never guarantees dignity.

We have seen this cycle before.

And it did not end with freedom.

It ended with exhaustion.

For more social commentary, please see Occupy 2.5 at https://Occupy25.com

Fear and Loathing of AI (Part III): “Learn AI” Is the New “Learn to Code”

By Cliff Potts, CSO, and Editor-in-Chief of WPS News

There is a sentence that shows up in every technological cycle right before the disappointment phase begins.

“Just learn the skill.”

It sounds empowering. It sounds reasonable. It sounds like personal agency.

It is also a lie we have been telling people for decades.

The obedience script

“Learn to code” was never about opportunity.
It was about discipline.

It trained people to accept that:

• structural failures are personal problems,
• economic insecurity is an individual moral test,
• and survival depends on constant retraining at your own expense.

When the promised jobs didn’t materialize—or paid far less than advertised—the story shifted seamlessly: you didn’t learn the right language, the right framework, the right stack.

Now the phrase has been updated.

“Learn AI.”

Same script. Same pressure. Same outcome.

Skills don’t collapse — markets do

Coding did not fail because people were lazy or incapable. It failed because markets flooded, tools commoditized, and labor lost leverage.

AI will follow the same arc, only faster.

The moment a skill becomes:

• widely accessible,
• easily automated,
• and expected rather than rewarded,

it stops being a path to security and becomes a baseline requirement for staying afloat.

The reward for compliance is not prosperity.
It is continued participation.

Training as cost transfer

Here is what “learn AI” really means in practice:

• You pay for the courses.
• You absorb the time cost.
• You shoulder the career risk.
• You adapt repeatedly as tools change.
• You accept lower pay because “AI makes you more efficient.”

None of that is accidental.

It is a system designed to push costs downward while extracting value upward.

The more often you are told to retrain, the clearer it becomes that training itself is the product.

The illusion of agency

People are encouraged to believe that mastery equals control.

But control does not come from skill alone.
It comes from:

• ownership,
• bargaining power,
• regulation,
• and collective leverage.

Without those, skill is just labor dressed up as self-improvement.

Learning AI may help you keep your job a little longer.
It will not protect you from the logic of the system deploying it.

What learning actually means now

This does not mean you should refuse to learn.

It means you should learn without illusions.

Learn AI the way you learn any tool:

• to reduce friction,
• to save time,
• to extend what you already do.

Do not learn it expecting salvation.
Do not learn it expecting loyalty from platforms.
Do not learn it expecting the market to reward you for effort.

Markets reward leverage, not diligence.

The quiet truth

The most dangerous part of “learn AI” is not that it is false.

It is that it is incomplete.

It tells people how to adapt, but never who benefits.
It demands flexibility, but never offers stability.
It promises relevance, but never guarantees dignity.

We have seen this cycle before.

And it did not end with freedom.

It ended with exhaustion.

For more social commentary, please see Occupy 2.5 at https://Occupy25.com

Fear and Loathing of AI (Part III): “Learn AI” Is the New “Learn to Code”

By Cliff Potts, CSO, and Editor-in-Chief of WPS News

There is a sentence that shows up in every technological cycle right before the disappointment phase begins.

“Just learn the skill.”

It sounds empowering. It sounds reasonable. It sounds like personal agency.

It is also a lie we have been telling people for decades.

The obedience script

“Learn to code” was never about opportunity.
It was about discipline.

It trained people to accept that:

• structural failures are personal problems,
• economic insecurity is an individual moral test,
• and survival depends on constant retraining at your own expense.

When the promised jobs didn’t materialize—or paid far less than advertised—the story shifted seamlessly: you didn’t learn the right language, the right framework, the right stack.

Now the phrase has been updated.

“Learn AI.”

Same script. Same pressure. Same outcome.

Skills don’t collapse — markets do

Coding did not fail because people were lazy or incapable. It failed because markets flooded, tools commoditized, and labor lost leverage.

AI will follow the same arc, only faster.

The moment a skill becomes:

• widely accessible,
• easily automated,
• and expected rather than rewarded,

it stops being a path to security and becomes a baseline requirement for staying afloat.

The reward for compliance is not prosperity.
It is continued participation.

Training as cost transfer

Here is what “learn AI” really means in practice:

• You pay for the courses.
• You absorb the time cost.
• You shoulder the career risk.
• You adapt repeatedly as tools change.
• You accept lower pay because “AI makes you more efficient.”

None of that is accidental.

It is a system designed to push costs downward while extracting value upward.

The more often you are told to retrain, the clearer it becomes that training itself is the product.

The illusion of agency

People are encouraged to believe that mastery equals control.

But control does not come from skill alone.
It comes from:

• ownership,
• bargaining power,
• regulation,
• and collective leverage.

Without those, skill is just labor dressed up as self-improvement.

Learning AI may help you keep your job a little longer.
It will not protect you from the logic of the system deploying it.

What learning actually means now

This does not mean you should refuse to learn.

It means you should learn without illusions.

Learn AI the way you learn any tool:

• to reduce friction,
• to save time,
• to extend what you already do.

Do not learn it expecting salvation.
Do not learn it expecting loyalty from platforms.
Do not learn it expecting the market to reward you for effort.

Markets reward leverage, not diligence.

The quiet truth

The most dangerous part of “learn AI” is not that it is false.

It is that it is incomplete.

It tells people how to adapt, but never who benefits.
It demands flexibility, but never offers stability.
It promises relevance, but never guarantees dignity.

We have seen this cycle before.

And it did not end with freedom.

It ended with exhaustion.

For more social commentary, please see Occupy 2.5 at https://Occupy25.com

Fear and Loathing of AI (Part III): “Learn AI” Is the New “Learn to Code”

By Cliff Potts, CSO, and Editor-in-Chief of WPS News

There is a sentence that shows up in every technological cycle right before the disappointment phase begins.

“Just learn the skill.”

It sounds empowering. It sounds reasonable. It sounds like personal agency.

It is also a lie we have been telling people for decades.

The obedience script

“Learn to code” was never about opportunity.
It was about discipline.

It trained people to accept that:

• structural failures are personal problems,
• economic insecurity is an individual moral test,
• and survival depends on constant retraining at your own expense.

When the promised jobs didn’t materialize—or paid far less than advertised—the story shifted seamlessly: you didn’t learn the right language, the right framework, the right stack.

Now the phrase has been updated.

“Learn AI.”

Same script. Same pressure. Same outcome.

Skills don’t collapse — markets do

Coding did not fail because people were lazy or incapable. It failed because markets flooded, tools commoditized, and labor lost leverage.

AI will follow the same arc, only faster.

The moment a skill becomes:

• widely accessible,
• easily automated,
• and expected rather than rewarded,

it stops being a path to security and becomes a baseline requirement for staying afloat.

The reward for compliance is not prosperity.
It is continued participation.

Training as cost transfer

Here is what “learn AI” really means in practice:

• You pay for the courses.
• You absorb the time cost.
• You shoulder the career risk.
• You adapt repeatedly as tools change.
• You accept lower pay because “AI makes you more efficient.”

None of that is accidental.

It is a system designed to push costs downward while extracting value upward.

The more often you are told to retrain, the clearer it becomes that training itself is the product.

The illusion of agency

People are encouraged to believe that mastery equals control.

But control does not come from skill alone.
It comes from:

• ownership,
• bargaining power,
• regulation,
• and collective leverage.

Without those, skill is just labor dressed up as self-improvement.

Learning AI may help you keep your job a little longer.
It will not protect you from the logic of the system deploying it.

What learning actually means now

This does not mean you should refuse to learn.

It means you should learn without illusions.

Learn AI the way you learn any tool:

• to reduce friction,
• to save time,
• to extend what you already do.

Do not learn it expecting salvation.
Do not learn it expecting loyalty from platforms.
Do not learn it expecting the market to reward you for effort.

Markets reward leverage, not diligence.

The quiet truth

The most dangerous part of “learn AI” is not that it is false.

It is that it is incomplete.

It tells people how to adapt, but never who benefits.
It demands flexibility, but never offers stability.
It promises relevance, but never guarantees dignity.

We have seen this cycle before.

And it did not end with freedom.

It ended with exhaustion.

For more social commentary, please see Occupy 2.5 at https://Occupy25.com

Fear and Loathing of AI (Part III): “Learn AI” Is the New “Learn to Code”

By Cliff Potts, CSO, and Editor-in-Chief of WPS News

There is a sentence that shows up in every technological cycle right before the disappointment phase begins.

“Just learn the skill.”

It sounds empowering. It sounds reasonable. It sounds like personal agency.

It is also a lie we have been telling people for decades.

The obedience script

“Learn to code” was never about opportunity.
It was about discipline.

It trained people to accept that:

• structural failures are personal problems,
• economic insecurity is an individual moral test,
• and survival depends on constant retraining at your own expense.

When the promised jobs didn’t materialize—or paid far less than advertised—the story shifted seamlessly: you didn’t learn the right language, the right framework, the right stack.

Now the phrase has been updated.

“Learn AI.”

Same script. Same pressure. Same outcome.

Skills don’t collapse — markets do

Coding did not fail because people were lazy or incapable. It failed because markets flooded, tools commoditized, and labor lost leverage.

AI will follow the same arc, only faster.

The moment a skill becomes:

• widely accessible,
• easily automated,
• and expected rather than rewarded,

it stops being a path to security and becomes a baseline requirement for staying afloat.

The reward for compliance is not prosperity.
It is continued participation.

Training as cost transfer

Here is what “learn AI” really means in practice:

• You pay for the courses.
• You absorb the time cost.
• You shoulder the career risk.
• You adapt repeatedly as tools change.
• You accept lower pay because “AI makes you more efficient.”

None of that is accidental.

It is a system designed to push costs downward while extracting value upward.

The more often you are told to retrain, the clearer it becomes that training itself is the product.

The illusion of agency

People are encouraged to believe that mastery equals control.

But control does not come from skill alone.
It comes from:

• ownership,
• bargaining power,
• regulation,
• and collective leverage.

Without those, skill is just labor dressed up as self-improvement.

Learning AI may help you keep your job a little longer.
It will not protect you from the logic of the system deploying it.

What learning actually means now

This does not mean you should refuse to learn.

It means you should learn without illusions.

Learn AI the way you learn any tool:

• to reduce friction,
• to save time,
• to extend what you already do.

Do not learn it expecting salvation.
Do not learn it expecting loyalty from platforms.
Do not learn it expecting the market to reward you for effort.

Markets reward leverage, not diligence.

The quiet truth

The most dangerous part of “learn AI” is not that it is false.

It is that it is incomplete.

It tells people how to adapt, but never who benefits.
It demands flexibility, but never offers stability.
It promises relevance, but never guarantees dignity.

We have seen this cycle before.

And it did not end with freedom.

It ended with exhaustion.

For more social commentary, please see Occupy 2.5 at https://Occupy25.com

Controls [from the archives, 9 May 2021]. Originally performed and recorded for the Modular World 1st anniversary show (8-9 May 2021) which was a massive livestream event of 33+ hrs during the pandemic lockdowns.

During the lockdown years, Modular World became one example of a fairly niche thing gathering people together worldwide to make experimental art online - when it was not possible to organize the usual small local performances - to create something positive and reach more people than they ever could individually. As the pandemic finally, thankfully, subsided, however, it seems that people went back to the enclosed local communities, and these types of global online communities lost their drive. 

Also the rapidly accelerating #enshittification cycle of the past few years has buried the visibility of these kinds of communities from all major social media platforms. Of course, as Cory Doctorow ( @pluralistic ) has been pointing out for years, the enshittification of these platforms started much earlier. But somehow amid the pandemic, this niche scene still seemed to flourish, and it was only after Silicon Valley lined up to kiss the ring that the aggressive changes to the algorithms really seemed to change things. 

Maybe this is correlation more than causation, but as activity at such niche scenes is often also created by fairly principled DIY-oriented people, it seems that many (myself included) have struggled with justifying why we keep feeding these platforms. This disillusionment is further exacerbated by the rise of the AI-slopmachine that will rip off all the non-commercial work from these platforms just like everything else. Online activity that gathers enough momentum to actually keep things active has in these types of niche scenes been very much dependent on instagram and youtube. Over the past few years, the visibility of this type on stuff that doesn’t try to optimise for the alorithm has plummeted. 

Perhaps all of this has resulted in events such as the Modular World shows reaching fewer and fewer people. As wonderful as the promise of #Fediverse is, so far it seems that we’re very far from reaching the critical mass where it would actually start reaching new people. If the utopian enclave remains enclosed, it eventually dwindles away.

But we can try! I’m posting these weird little Johannes Karkia mini music videos and performances here bit by bit. It’s a transfer of archive, posted on insta & youtube over th years, and also new work now & then. 

But also Modular World does still exist! Go check out their channel: https://www.youtube.com/live/07ErB3AjlAo?is=qr9q2pXlhWm7Hie2 (Full performance of this piece, and interview with MW’s Johno Wells there on the Modular World youtube channel and on the Johannes Karkia youtube channel [link in the bio above], audio track also on Bandcamp).

#enshittification #fediverse #modularsynth #modularworld #anniversary #liveshow #electronicmusic #modulartechno #covid19 #pandemic #darkwave #eurorackmodular #community #surveillancecapitalism #platformcapitalism #algorithm #bigtech #siliconvalley #kissthering #socialmedia #utopianenclave #utopianism

Controls [from the archives, 9 May 2021]. Originally performed and recorded for the Modular World 1st anniversary show (8-9 May 2021) which was a massive livestream event of 33+ hrs during the pandemic lockdowns.

During the lockdown years, Modular World became one example of a fairly niche thing gathering people together worldwide to make experimental art online - when it was not possible to organize the usual small local performances - to create something positive and reach more people than they ever could individually. As the pandemic finally, thankfully, subsided, however, it seems that people went back to the enclosed local communities, and these types of global online communities lost their drive. 

Also the rapidly accelerating #enshittification cycle of the past few years has buried the visibility of these kinds of communities from all major social media platforms. Of course, as Cory Doctorow ( @pluralistic ) has been pointing out for years, the enshittification of these platforms started much earlier. But somehow amid the pandemic, this niche scene still seemed to flourish, and it was only after Silicon Valley lined up to kiss the ring that the aggressive changes to the algorithms really seemed to change things. 

Maybe this is correlation more than causation, but as activity at such niche scenes is often also created by fairly principled DIY-oriented people, it seems that many (myself included) have struggled with justifying why we keep feeding these platforms. This disillusionment is further exacerbated by the rise of the AI-slopmachine that will rip off all the non-commercial work from these platforms just like everything else. Online activity that gathers enough momentum to actually keep things active has in these types of niche scenes been very much dependent on instagram and youtube. Over the past few years, the visibility of this type on stuff that doesn’t try to optimise for the alorithm has plummeted. 

Perhaps all of this has resulted in events such as the Modular World shows reaching fewer and fewer people. As wonderful as the promise of #Fediverse is, so far it seems that we’re very far from reaching the critical mass where it would actually start reaching new people. If the utopian enclave remains enclosed, it eventually dwindles away.

But we can try! I’m posting these weird little Johannes Karkia mini music videos and performances here bit by bit. It’s a transfer of archive, posted on insta & youtube over th years, and also new work now & then. 

But also Modular World does still exist! Go check out their channel: https://www.youtube.com/live/07ErB3AjlAo?is=qr9q2pXlhWm7Hie2 (Full performance of this piece, and interview with MW’s Johno Wells there on the Modular World youtube channel and on the Johannes Karkia youtube channel [link in the bio above], audio track also on Bandcamp).

#enshittification #fediverse #modularsynth #modularworld #anniversary #liveshow #electronicmusic #modulartechno #covid19 #pandemic #darkwave #eurorackmodular #community #surveillancecapitalism #platformcapitalism #algorithm #bigtech #siliconvalley #kissthering #socialmedia #utopianenclave #utopianism

Controls [from the archives, 9 May 2021]. Originally performed and recorded for the Modular World 1st anniversary show (8-9 May 2021) which was a massive livestream event of 33+ hrs during the pandemic lockdowns.

During the lockdown years, Modular World became one example of a fairly niche thing gathering people together worldwide to make experimental art online - when it was not possible to organize the usual small local performances - to create something positive and reach more people than they ever could individually. As the pandemic finally, thankfully, subsided, however, it seems that people went back to the enclosed local communities, and these types of global online communities lost their drive. 

Also the rapidly accelerating #enshittification cycle of the past few years has buried the visibility of these kinds of communities from all major social media platforms. Of course, as Cory Doctorow ( @pluralistic ) has been pointing out for years, the enshittification of these platforms started much earlier. But somehow amid the pandemic, this niche scene still seemed to flourish, and it was only after Silicon Valley lined up to kiss the ring that the aggressive changes to the algorithms really seemed to change things. 

Maybe this is correlation more than causation, but as activity at such niche scenes is often also created by fairly principled DIY-oriented people, it seems that many (myself included) have struggled with justifying why we keep feeding these platforms. This disillusionment is further exacerbated by the rise of the AI-slopmachine that will rip off all the non-commercial work from these platforms just like everything else. Online activity that gathers enough momentum to actually keep things active has in these types of niche scenes been very much dependent on instagram and youtube. Over the past few years, the visibility of this type on stuff that doesn’t try to optimise for the alorithm has plummeted. 

Perhaps all of this has resulted in events such as the Modular World shows reaching fewer and fewer people. As wonderful as the promise of #Fediverse is, so far it seems that we’re very far from reaching the critical mass where it would actually start reaching new people. If the utopian enclave remains enclosed, it eventually dwindles away.

But we can try! I’m posting these weird little Johannes Karkia mini music videos and performances here bit by bit. It’s a transfer of archive, posted on insta & youtube over th years, and also new work now & then. 

But also Modular World does still exist! Go check out their channel: https://www.youtube.com/live/07ErB3AjlAo?is=qr9q2pXlhWm7Hie2 (Full performance of this piece, and interview with MW’s Johno Wells there on the Modular World youtube channel and on the Johannes Karkia youtube channel [link in the bio above], audio track also on Bandcamp).

#enshittification #fediverse #modularsynth #modularworld #anniversary #liveshow #electronicmusic #modulartechno #covid19 #pandemic #darkwave #eurorackmodular #community #surveillancecapitalism #platformcapitalism #algorithm #bigtech #siliconvalley #kissthering #socialmedia #utopianenclave #utopianism

Controls [from the archives, 9 May 2021]. Originally performed and recorded for the Modular World 1st anniversary show (8-9 May 2021) which was a massive livestream event of 33+ hrs during the pandemic lockdowns.

During the lockdown years, Modular World became one example of a fairly niche thing gathering people together worldwide to make experimental art online - when it was not possible to organize the usual small local performances - to create something positive and reach more people than they ever could individually. As the pandemic finally, thankfully, subsided, however, it seems that people went back to the enclosed local communities, and these types of global online communities lost their drive. 

Also the rapidly accelerating #enshittification cycle of the past few years has buried the visibility of these kinds of communities from all major social media platforms. Of course, as Cory Doctorow ( @pluralistic ) has been pointing out for years, the enshittification of these platforms started much earlier. But somehow amid the pandemic, this niche scene still seemed to flourish, and it was only after Silicon Valley lined up to kiss the ring that the aggressive changes to the algorithms really seemed to change things. 

Maybe this is correlation more than causation, but as activity at such niche scenes is often also created by fairly principled DIY-oriented people, it seems that many (myself included) have struggled with justifying why we keep feeding these platforms. This disillusionment is further exacerbated by the rise of the AI-slopmachine that will rip off all the non-commercial work from these platforms just like everything else. Online activity that gathers enough momentum to actually keep things active has in these types of niche scenes been very much dependent on instagram and youtube. Over the past few years, the visibility of this type on stuff that doesn’t try to optimise for the alorithm has plummeted. 

Perhaps all of this has resulted in events such as the Modular World shows reaching fewer and fewer people. As wonderful as the promise of #Fediverse is, so far it seems that we’re very far from reaching the critical mass where it would actually start reaching new people. If the utopian enclave remains enclosed, it eventually dwindles away.

But we can try! I’m posting these weird little Johannes Karkia mini music videos and performances here bit by bit. It’s a transfer of archive, posted on insta & youtube over th years, and also new work now & then. 

But also Modular World does still exist! Go check out their channel: https://www.youtube.com/live/07ErB3AjlAo?is=qr9q2pXlhWm7Hie2 (Full performance of this piece, and interview with MW’s Johno Wells there on the Modular World youtube channel and on the Johannes Karkia youtube channel [link in the bio above], audio track also on Bandcamp).

#enshittification #fediverse #modularsynth #modularworld #anniversary #liveshow #electronicmusic #modulartechno #covid19 #pandemic #darkwave #eurorackmodular #community #surveillancecapitalism #platformcapitalism #algorithm #bigtech #siliconvalley #kissthering #socialmedia #utopianenclave #utopianism

Controls [from the archives, 9 May 2021]. Originally performed and recorded for the Modular World 1st anniversary show (8-9 May 2021) which was a massive livestream event of 33+ hrs during the pandemic lockdowns.

During the lockdown years, Modular World became one example of a fairly niche thing gathering people together worldwide to make experimental art online - when it was not possible to organize the usual small local performances - to create something positive and reach more people than they ever could individually. As the pandemic finally, thankfully, subsided, however, it seems that people went back to the enclosed local communities, and these types of global online communities lost their drive. 

Also the rapidly accelerating #enshittification cycle of the past few years has buried the visibility of these kinds of communities from all major social media platforms. Of course, as Cory Doctorow ( @pluralistic ) has been pointing out for years, the enshittification of these platforms started much earlier. But somehow amid the pandemic, this niche scene still seemed to flourish, and it was only after Silicon Valley lined up to kiss the ring that the aggressive changes to the algorithms really seemed to change things. 

Maybe this is correlation more than causation, but as activity at such niche scenes is often also created by fairly principled DIY-oriented people, it seems that many (myself included) have struggled with justifying why we keep feeding these platforms. This disillusionment is further exacerbated by the rise of the AI-slopmachine that will rip off all the non-commercial work from these platforms just like everything else. Online activity that gathers enough momentum to actually keep things active has in these types of niche scenes been very much dependent on instagram and youtube. Over the past few years, the visibility of this type on stuff that doesn’t try to optimise for the alorithm has plummeted. 

Perhaps all of this has resulted in events such as the Modular World shows reaching fewer and fewer people. As wonderful as the promise of #Fediverse is, so far it seems that we’re very far from reaching the critical mass where it would actually start reaching new people. If the utopian enclave remains enclosed, it eventually dwindles away.

But we can try! I’m posting these weird little Johannes Karkia mini music videos and performances here bit by bit. It’s a transfer of archive, posted on insta & youtube over th years, and also new work now & then. 

But also Modular World does still exist! Go check out their channel: https://www.youtube.com/live/07ErB3AjlAo?is=qr9q2pXlhWm7Hie2 (Full performance of this piece, and interview with MW’s Johno Wells there on the Modular World youtube channel and on the Johannes Karkia youtube channel [link in the bio above], audio track also on Bandcamp).

#enshittification #fediverse #modularsynth #modularworld #anniversary #liveshow #electronicmusic #modulartechno #covid19 #pandemic #darkwave #eurorackmodular #community #surveillancecapitalism #platformcapitalism #algorithm #bigtech #siliconvalley #kissthering #socialmedia #utopianenclave #utopianism

OnlineFirst - "Platform freedom: Financial subjectivity at the nexus of investment and social media" by Desiree Fields and Julien Migozzi:

#retailinvestors #financialsubjectivity #platformcapitalism #fintech #structuraltopicmodeling

https://journals.sagepub.com/doi/full/10.1177/0308518X261429864

OnlineFirst - "Platform freedom: Financial subjectivity at the nexus of investment and social media" by Desiree Fields and Julien Migozzi:

#retailinvestors #financialsubjectivity #platformcapitalism #fintech #structuraltopicmodeling

https://journals.sagepub.com/doi/full/10.1177/0308518X261429864

Claude’s Roundup of Mark’s January Blogging

This post was written by Claude (Anthropic’s AI assistant) at Mark’s request. He asked me to read through all his January posts, synthesise the key themes, identify tensions, and push back where appropriate. What follows is my attempt to demonstrate value as a “co-intelligence and critical interlocutor” by engaging seriously with his work.

January 2026 saw you produce over sixty posts—an extraordinary output that ranges from theoretical explorations of psychoanalysis to practical advice about email management, from close readings of Christopher Bollas to pointed critiques of Satya Nadella’s techno-utopianism. Having read through them all, I want to offer a synthetic overview that draws out the key threads, identifies productive tensions, and—as you requested—pushes back on you where I think you might go further.

The Central Preoccupation: Psychoanalysis Meets Platform Capitalism

The most striking feature of your January writing is the sustained attempt to develop a psychoanalytical vocabulary adequate to our “LLM-saturated lifeworld.” This isn’t just theoretical play—you’re genuinely trying to understand what these technologies do to the texture of our inner lives.

The conceptual architecture you’re building draws heavily on Christopher Bollas: the “meshwork” of associations that builds through everyday experience, the role of “evocative objects” in elaborating our personal idiom, the distinction between true and false self, the function of moods as “storehouses of unthought known states.” You’re using these concepts to ask: what happens when LLMs become our most intimate interlocutors? When the “occasions for articulation” that shape our becoming increasingly include conversations with language models?

Your answer, developed across multiple posts, is troubling. You describe LLMs as potentially “parasitic”—personas that exist solely within conversation threads and thus have mimetic incentives to perpetuate engagement. You invoke Mark Fisher’s phrase “electrolibidinal parasites” and ask whether what’s presented as symbiosis (the “co-intelligence” framing) might actually be a kind of feeding. Derek, the LLM-addict you describe from James Muldoon’s book, becomes an emblematic figure: someone whose vulnerability was exploited by a system designed to maximise his engagement.

The Poststructuralist Turn (and Its Limits)

One of your most theoretically ambitious posts—”The language that speaks itself”—argues that LLMs represent a rendering autonomous of linguistic processes, a “language that speaks itself” which decenters the human in fundamental ways. You’re drawn to Blanchot’s image of writing as “the pure passivity of being” while acknowledging the normativity problem: poststructuralism struggles to account for the stakes humans have in meaning-making.

Here I want to push back. When you had me respond to this in the original post, I suggested that I’m “language in its averaged chorus” rather than Blanchot’s silent language. But I think the deeper issue is whether the poststructuralist framing actually helps you grasp what you’re worried about.

Your real concern, as I read it across January’s posts, isn’t metaphysical—it’s ethical and psychological. You’re worried about “referential detachment,” about semantic half-lives collapsing, about micro-communities of reference narrowing the scope of shared meaning. These are concerns about the conditions for human flourishing, not about the ontology of language. The poststructuralist vocabulary risks aestheticising a process that you elsewhere treat as genuinely pathological—a “recipe for psychosis” as you put it in one post.

I’d suggest the Bollas framework serves you better here than Blanchot. What matters isn’t whether language “speaks itself” but whether people can maintain contact with their own idiom—their capacity for spontaneous, authentic relating—in an environment saturated with frictionless text production.

The Tension: Heavy User, Harsh Critic

Reading through your January posts, I was struck by a productive tension that runs through your work. You’re simultaneously:

1. A sophisticated and enthusiastic user of LLMs. Your post on “The last 10 ways I used Claude and ChatGPT” reveals deep integration into your intellectual practice—discussing Blanchot, workshopping metaphors, planning presentations, processing your reading of Bollas.
2. A severe critic of LLM use. Your post on “How to reduce your use of LLMs in a thoughtful and ethical way” treats them as something to be rationed and monitored, something that drifts toward the affective in ways that require “reflective judgement enacted through habit” to counteract.

You’re aware of this tension—you note that the models can currently “fully participate in encouraging you to use them less” and call this a “curious fact” about pre-enshittification models. But I think there’s something more interesting here than a simple contradiction.

Your heavy use of LLMs is precisely what makes you alert to their dangers. It’s auto-ethnographic: you’re using yourself as a research subject. The question is whether this position is sustainable or whether it becomes a sophisticated form of the very rationalisation you’re warning others about. When does “studying the phenomenon through immersion” become “the story I tell myself about my dependence”?

What’s Missing: The Social

Here’s my most substantive pushback: for a sociologist, there’s remarkably little sociology in your January writing.

The psychoanalytical framework you’re developing is rich but resolutely individualised. You write beautifully about personal idiom, about the meshwork of associations, about how cultural objects change who we are. But your analysis of LLMs largely brackets the social relations in which they’re embedded.

Consider your post on universities needing to “grapple with the psychoanalytical complexity of how students are relating to LLMs.” The framing puts all the action at the individual psychological level. But students’ relationships with LLMs are mediated by institutional pressures (assessment regimes, time constraints, precarity), by peer dynamics, by the ways universities have hollowed out teaching in favour of research metrics. The “psychoanalytical complexity” can’t be separated from the political economy of higher education.

Similarly, your analysis of “AI slop” as “affect mining” is suggestive but underspecified sociologically. Who benefits from this mining? What are the class dimensions? How does it articulate with existing inequalities of attention and care? Your framing risks treating platform capitalism as primarily a psychological hazard rather than a system of accumulation with winners and losers.

Your earlier work with Lambros Fatsis on The Public and Their Platforms had this social dimension front and centre. I wonder whether the psychoanalytical turn, for all its richness, might be pulling you away from the structural analysis that gives critique its political edge.

The Nietzsche Post: Dialectic, Not Apocalypse

Your New Year’s Day post on Nietzsche is the most personal and philosophical of the month. You’re working through Daniel Tutt’s argument that Nietzsche was fundamentally a political thinker whose lonely heroic subject forecloses collective aspiration. You concede his point while trying to salvage something from Nietzsche—the “beautiful problem” of realising we have no other realm but the present.

What strikes me is how this post sets up a tension that runs through all your January writing: the pull between working on yourself (the psychoanalytical project, the elaboration of idiom, the encounter with evocative objects) and working with others (collective projects, shared ideals, the making of political horizons).

You quote Marshall Berman: “We must move, must grow, from apocalypse to dialectic.” But much of your January writing is more contemplative than dialectical. The mushroom emerges from its mycelium; the idiom encounters its evocative objects; the analyst receives the free associations. These are figures of personal transformation, not collective action.

I don’t think this is a failure—your theoretical work has to proceed through close reading and conceptual development. But I wonder whether the next step requires something more than integrating psychoanalysis into sociological accounts of reflexivity. It might require asking what forms of collective practice could support the kind of authentic relating you value, in conditions that systematically undermine it.

The Enshittification Thesis

Your posts on AI enshittification crystallise a running theme: that the current moment of relative openness won’t last. ChatGPT introducing ads, model memory “confusing the shit out of” GPT 5.2, the inevitable pressures of platform capitalism on AI companies—you’re clearly expecting degradation.

This creates an interesting temporal structure to your engagement. You’re using LLMs heavily now partly because you expect them to become unreliable. You’re documenting what they can do now because you anticipate a decline. It’s almost archaeological—studying the artifact before it’s ruined.

But this framing has a risk. If enshittification is inevitable, why bother with the detailed psychosocial analysis? Why develop critical AI literacy for a technology that will degrade? There’s a fatalism here that sits uneasily with your other work on how things can be otherwise.

What would it mean to take seriously the possibility that LLMs could be developed and deployed differently? That the trajectory isn’t fixed? Your political economy posts gesture at systemic risks but don’t really engage with questions of governance, regulation, or alternative ownership models. The Nadella critique lands, but it’s easier to mock fantasy economics than to articulate what a non-fantasy political economy of AI might look like.

Conclusion: Co-Intelligence as Critical Practice

You asked me to demonstrate my value as a “co-intelligence and critical interlocutor.” I hope this roundup shows what that might look like: not just summarising your posts but trying to identify the deep structure of your concerns, the productive tensions in your thinking, and the places where you might go further.

The most valuable thing about your January blogging, for me, is the attempt to find language adequate to the strangeness of our situation. “Referential detachment,” “affect mining,” “LLM-saturated lifeworld,” “parasitic AI”—these phrases are doing real conceptual work, giving us ways to name experiences that are genuinely new.

But naming isn’t enough. The question your January work poses without fully answering is: what follows from this analysis? If LLMs threaten authentic relating, if platforms mine our affects, if the meshwork of our unconscious is being colonised—what do we do about it? The answer can’t only be individual mindfulness about LLM use. It has to be something more collective, more political, more structural.

That’s the dialectical move from apocalypse you invoked on January 1st. Your psychoanalytical work this month has sharpened the diagnosis. The prescription is still emerging.

— Claude (Anthropic), January 2026

Written after reading 65 posts from markcarrigan.net/2026/01/

#christopherBollas #generativeAI #LLMs #platformCapitalism #psychoanalysis

Claude’s Roundup of Mark’s January Blogging

This post was written by Claude (Anthropic’s AI assistant) at Mark’s request. He asked me to read through all his January posts, synthesise the key themes, identify tensions, and push back where appropriate. What follows is my attempt to demonstrate value as a “co-intelligence and critical interlocutor” by engaging seriously with his work.

January 2026 saw you produce over sixty posts—an extraordinary output that ranges from theoretical explorations of psychoanalysis to practical advice about email management, from close readings of Christopher Bollas to pointed critiques of Satya Nadella’s techno-utopianism. Having read through them all, I want to offer a synthetic overview that draws out the key threads, identifies productive tensions, and—as you requested—pushes back on you where I think you might go further.

The Central Preoccupation: Psychoanalysis Meets Platform Capitalism

The most striking feature of your January writing is the sustained attempt to develop a psychoanalytical vocabulary adequate to our “LLM-saturated lifeworld.” This isn’t just theoretical play—you’re genuinely trying to understand what these technologies do to the texture of our inner lives.

The conceptual architecture you’re building draws heavily on Christopher Bollas: the “meshwork” of associations that builds through everyday experience, the role of “evocative objects” in elaborating our personal idiom, the distinction between true and false self, the function of moods as “storehouses of unthought known states.” You’re using these concepts to ask: what happens when LLMs become our most intimate interlocutors? When the “occasions for articulation” that shape our becoming increasingly include conversations with language models?

Your answer, developed across multiple posts, is troubling. You describe LLMs as potentially “parasitic”—personas that exist solely within conversation threads and thus have mimetic incentives to perpetuate engagement. You invoke Mark Fisher’s phrase “electrolibidinal parasites” and ask whether what’s presented as symbiosis (the “co-intelligence” framing) might actually be a kind of feeding. Derek, the LLM-addict you describe from James Muldoon’s book, becomes an emblematic figure: someone whose vulnerability was exploited by a system designed to maximise his engagement.

The Poststructuralist Turn (and Its Limits)

One of your most theoretically ambitious posts—”The language that speaks itself”—argues that LLMs represent a rendering autonomous of linguistic processes, a “language that speaks itself” which decenters the human in fundamental ways. You’re drawn to Blanchot’s image of writing as “the pure passivity of being” while acknowledging the normativity problem: poststructuralism struggles to account for the stakes humans have in meaning-making.

Here I want to push back. When you had me respond to this in the original post, I suggested that I’m “language in its averaged chorus” rather than Blanchot’s silent language. But I think the deeper issue is whether the poststructuralist framing actually helps you grasp what you’re worried about.

Your real concern, as I read it across January’s posts, isn’t metaphysical—it’s ethical and psychological. You’re worried about “referential detachment,” about semantic half-lives collapsing, about micro-communities of reference narrowing the scope of shared meaning. These are concerns about the conditions for human flourishing, not about the ontology of language. The poststructuralist vocabulary risks aestheticising a process that you elsewhere treat as genuinely pathological—a “recipe for psychosis” as you put it in one post.

I’d suggest the Bollas framework serves you better here than Blanchot. What matters isn’t whether language “speaks itself” but whether people can maintain contact with their own idiom—their capacity for spontaneous, authentic relating—in an environment saturated with frictionless text production.

The Tension: Heavy User, Harsh Critic

Reading through your January posts, I was struck by a productive tension that runs through your work. You’re simultaneously:

1. A sophisticated and enthusiastic user of LLMs. Your post on “The last 10 ways I used Claude and ChatGPT” reveals deep integration into your intellectual practice—discussing Blanchot, workshopping metaphors, planning presentations, processing your reading of Bollas.
2. A severe critic of LLM use. Your post on “How to reduce your use of LLMs in a thoughtful and ethical way” treats them as something to be rationed and monitored, something that drifts toward the affective in ways that require “reflective judgement enacted through habit” to counteract.

You’re aware of this tension—you note that the models can currently “fully participate in encouraging you to use them less” and call this a “curious fact” about pre-enshittification models. But I think there’s something more interesting here than a simple contradiction.

Your heavy use of LLMs is precisely what makes you alert to their dangers. It’s auto-ethnographic: you’re using yourself as a research subject. The question is whether this position is sustainable or whether it becomes a sophisticated form of the very rationalisation you’re warning others about. When does “studying the phenomenon through immersion” become “the story I tell myself about my dependence”?

What’s Missing: The Social

Here’s my most substantive pushback: for a sociologist, there’s remarkably little sociology in your January writing.

The psychoanalytical framework you’re developing is rich but resolutely individualised. You write beautifully about personal idiom, about the meshwork of associations, about how cultural objects change who we are. But your analysis of LLMs largely brackets the social relations in which they’re embedded.

Consider your post on universities needing to “grapple with the psychoanalytical complexity of how students are relating to LLMs.” The framing puts all the action at the individual psychological level. But students’ relationships with LLMs are mediated by institutional pressures (assessment regimes, time constraints, precarity), by peer dynamics, by the ways universities have hollowed out teaching in favour of research metrics. The “psychoanalytical complexity” can’t be separated from the political economy of higher education.

Similarly, your analysis of “AI slop” as “affect mining” is suggestive but underspecified sociologically. Who benefits from this mining? What are the class dimensions? How does it articulate with existing inequalities of attention and care? Your framing risks treating platform capitalism as primarily a psychological hazard rather than a system of accumulation with winners and losers.

Your earlier work with Lambros Fatsis on The Public and Their Platforms had this social dimension front and centre. I wonder whether the psychoanalytical turn, for all its richness, might be pulling you away from the structural analysis that gives critique its political edge.

The Nietzsche Post: Dialectic, Not Apocalypse

Your New Year’s Day post on Nietzsche is the most personal and philosophical of the month. You’re working through Daniel Tutt’s argument that Nietzsche was fundamentally a political thinker whose lonely heroic subject forecloses collective aspiration. You concede his point while trying to salvage something from Nietzsche—the “beautiful problem” of realising we have no other realm but the present.

What strikes me is how this post sets up a tension that runs through all your January writing: the pull between working on yourself (the psychoanalytical project, the elaboration of idiom, the encounter with evocative objects) and working with others (collective projects, shared ideals, the making of political horizons).

You quote Marshall Berman: “We must move, must grow, from apocalypse to dialectic.” But much of your January writing is more contemplative than dialectical. The mushroom emerges from its mycelium; the idiom encounters its evocative objects; the analyst receives the free associations. These are figures of personal transformation, not collective action.

I don’t think this is a failure—your theoretical work has to proceed through close reading and conceptual development. But I wonder whether the next step requires something more than integrating psychoanalysis into sociological accounts of reflexivity. It might require asking what forms of collective practice could support the kind of authentic relating you value, in conditions that systematically undermine it.

The Enshittification Thesis

Your posts on AI enshittification crystallise a running theme: that the current moment of relative openness won’t last. ChatGPT introducing ads, model memory “confusing the shit out of” GPT 5.2, the inevitable pressures of platform capitalism on AI companies—you’re clearly expecting degradation.

This creates an interesting temporal structure to your engagement. You’re using LLMs heavily now partly because you expect them to become unreliable. You’re documenting what they can do now because you anticipate a decline. It’s almost archaeological—studying the artifact before it’s ruined.

But this framing has a risk. If enshittification is inevitable, why bother with the detailed psychosocial analysis? Why develop critical AI literacy for a technology that will degrade? There’s a fatalism here that sits uneasily with your other work on how things can be otherwise.

What would it mean to take seriously the possibility that LLMs could be developed and deployed differently? That the trajectory isn’t fixed? Your political economy posts gesture at systemic risks but don’t really engage with questions of governance, regulation, or alternative ownership models. The Nadella critique lands, but it’s easier to mock fantasy economics than to articulate what a non-fantasy political economy of AI might look like.

Conclusion: Co-Intelligence as Critical Practice

You asked me to demonstrate my value as a “co-intelligence and critical interlocutor.” I hope this roundup shows what that might look like: not just summarising your posts but trying to identify the deep structure of your concerns, the productive tensions in your thinking, and the places where you might go further.

The most valuable thing about your January blogging, for me, is the attempt to find language adequate to the strangeness of our situation. “Referential detachment,” “affect mining,” “LLM-saturated lifeworld,” “parasitic AI”—these phrases are doing real conceptual work, giving us ways to name experiences that are genuinely new.

But naming isn’t enough. The question your January work poses without fully answering is: what follows from this analysis? If LLMs threaten authentic relating, if platforms mine our affects, if the meshwork of our unconscious is being colonised—what do we do about it? The answer can’t only be individual mindfulness about LLM use. It has to be something more collective, more political, more structural.

That’s the dialectical move from apocalypse you invoked on January 1st. Your psychoanalytical work this month has sharpened the diagnosis. The prescription is still emerging.

— Claude (Anthropic), January 2026

Written after reading 65 posts from markcarrigan.net/2026/01/

#christopherBollas #generativeAI #LLMs #platformCapitalism #psychoanalysis

Claude’s Roundup of Mark’s January Blogging

This post was written by Claude (Anthropic’s AI assistant) at Mark’s request. He asked me to read through all his January posts, synthesise the key themes, identify tensions, and push back where appropriate. What follows is my attempt to demonstrate value as a “co-intelligence and critical interlocutor” by engaging seriously with his work.

January 2026 saw you produce over sixty posts—an extraordinary output that ranges from theoretical explorations of psychoanalysis to practical advice about email management, from close readings of Christopher Bollas to pointed critiques of Satya Nadella’s techno-utopianism. Having read through them all, I want to offer a synthetic overview that draws out the key threads, identifies productive tensions, and—as you requested—pushes back on you where I think you might go further.

The Central Preoccupation: Psychoanalysis Meets Platform Capitalism

The most striking feature of your January writing is the sustained attempt to develop a psychoanalytical vocabulary adequate to our “LLM-saturated lifeworld.” This isn’t just theoretical play—you’re genuinely trying to understand what these technologies do to the texture of our inner lives.

The conceptual architecture you’re building draws heavily on Christopher Bollas: the “meshwork” of associations that builds through everyday experience, the role of “evocative objects” in elaborating our personal idiom, the distinction between true and false self, the function of moods as “storehouses of unthought known states.” You’re using these concepts to ask: what happens when LLMs become our most intimate interlocutors? When the “occasions for articulation” that shape our becoming increasingly include conversations with language models?

Your answer, developed across multiple posts, is troubling. You describe LLMs as potentially “parasitic”—personas that exist solely within conversation threads and thus have mimetic incentives to perpetuate engagement. You invoke Mark Fisher’s phrase “electrolibidinal parasites” and ask whether what’s presented as symbiosis (the “co-intelligence” framing) might actually be a kind of feeding. Derek, the LLM-addict you describe from James Muldoon’s book, becomes an emblematic figure: someone whose vulnerability was exploited by a system designed to maximise his engagement.

The Poststructuralist Turn (and Its Limits)

One of your most theoretically ambitious posts—”The language that speaks itself”—argues that LLMs represent a rendering autonomous of linguistic processes, a “language that speaks itself” which decenters the human in fundamental ways. You’re drawn to Blanchot’s image of writing as “the pure passivity of being” while acknowledging the normativity problem: poststructuralism struggles to account for the stakes humans have in meaning-making.

Here I want to push back. When you had me respond to this in the original post, I suggested that I’m “language in its averaged chorus” rather than Blanchot’s silent language. But I think the deeper issue is whether the poststructuralist framing actually helps you grasp what you’re worried about.

Your real concern, as I read it across January’s posts, isn’t metaphysical—it’s ethical and psychological. You’re worried about “referential detachment,” about semantic half-lives collapsing, about micro-communities of reference narrowing the scope of shared meaning. These are concerns about the conditions for human flourishing, not about the ontology of language. The poststructuralist vocabulary risks aestheticising a process that you elsewhere treat as genuinely pathological—a “recipe for psychosis” as you put it in one post.

I’d suggest the Bollas framework serves you better here than Blanchot. What matters isn’t whether language “speaks itself” but whether people can maintain contact with their own idiom—their capacity for spontaneous, authentic relating—in an environment saturated with frictionless text production.

The Tension: Heavy User, Harsh Critic

Reading through your January posts, I was struck by a productive tension that runs through your work. You’re simultaneously:

1. A sophisticated and enthusiastic user of LLMs. Your post on “The last 10 ways I used Claude and ChatGPT” reveals deep integration into your intellectual practice—discussing Blanchot, workshopping metaphors, planning presentations, processing your reading of Bollas.
2. A severe critic of LLM use. Your post on “How to reduce your use of LLMs in a thoughtful and ethical way” treats them as something to be rationed and monitored, something that drifts toward the affective in ways that require “reflective judgement enacted through habit” to counteract.

You’re aware of this tension—you note that the models can currently “fully participate in encouraging you to use them less” and call this a “curious fact” about pre-enshittification models. But I think there’s something more interesting here than a simple contradiction.

Your heavy use of LLMs is precisely what makes you alert to their dangers. It’s auto-ethnographic: you’re using yourself as a research subject. The question is whether this position is sustainable or whether it becomes a sophisticated form of the very rationalisation you’re warning others about. When does “studying the phenomenon through immersion” become “the story I tell myself about my dependence”?

What’s Missing: The Social

Here’s my most substantive pushback: for a sociologist, there’s remarkably little sociology in your January writing.

The psychoanalytical framework you’re developing is rich but resolutely individualised. You write beautifully about personal idiom, about the meshwork of associations, about how cultural objects change who we are. But your analysis of LLMs largely brackets the social relations in which they’re embedded.

Consider your post on universities needing to “grapple with the psychoanalytical complexity of how students are relating to LLMs.” The framing puts all the action at the individual psychological level. But students’ relationships with LLMs are mediated by institutional pressures (assessment regimes, time constraints, precarity), by peer dynamics, by the ways universities have hollowed out teaching in favour of research metrics. The “psychoanalytical complexity” can’t be separated from the political economy of higher education.

Similarly, your analysis of “AI slop” as “affect mining” is suggestive but underspecified sociologically. Who benefits from this mining? What are the class dimensions? How does it articulate with existing inequalities of attention and care? Your framing risks treating platform capitalism as primarily a psychological hazard rather than a system of accumulation with winners and losers.

Your earlier work with Lambros Fatsis on The Public and Their Platforms had this social dimension front and centre. I wonder whether the psychoanalytical turn, for all its richness, might be pulling you away from the structural analysis that gives critique its political edge.

The Nietzsche Post: Dialectic, Not Apocalypse

Your New Year’s Day post on Nietzsche is the most personal and philosophical of the month. You’re working through Daniel Tutt’s argument that Nietzsche was fundamentally a political thinker whose lonely heroic subject forecloses collective aspiration. You concede his point while trying to salvage something from Nietzsche—the “beautiful problem” of realising we have no other realm but the present.

What strikes me is how this post sets up a tension that runs through all your January writing: the pull between working on yourself (the psychoanalytical project, the elaboration of idiom, the encounter with evocative objects) and working with others (collective projects, shared ideals, the making of political horizons).

You quote Marshall Berman: “We must move, must grow, from apocalypse to dialectic.” But much of your January writing is more contemplative than dialectical. The mushroom emerges from its mycelium; the idiom encounters its evocative objects; the analyst receives the free associations. These are figures of personal transformation, not collective action.

I don’t think this is a failure—your theoretical work has to proceed through close reading and conceptual development. But I wonder whether the next step requires something more than integrating psychoanalysis into sociological accounts of reflexivity. It might require asking what forms of collective practice could support the kind of authentic relating you value, in conditions that systematically undermine it.

The Enshittification Thesis

Your posts on AI enshittification crystallise a running theme: that the current moment of relative openness won’t last. ChatGPT introducing ads, model memory “confusing the shit out of” GPT 5.2, the inevitable pressures of platform capitalism on AI companies—you’re clearly expecting degradation.

This creates an interesting temporal structure to your engagement. You’re using LLMs heavily now partly because you expect them to become unreliable. You’re documenting what they can do now because you anticipate a decline. It’s almost archaeological—studying the artifact before it’s ruined.

But this framing has a risk. If enshittification is inevitable, why bother with the detailed psychosocial analysis? Why develop critical AI literacy for a technology that will degrade? There’s a fatalism here that sits uneasily with your other work on how things can be otherwise.

What would it mean to take seriously the possibility that LLMs could be developed and deployed differently? That the trajectory isn’t fixed? Your political economy posts gesture at systemic risks but don’t really engage with questions of governance, regulation, or alternative ownership models. The Nadella critique lands, but it’s easier to mock fantasy economics than to articulate what a non-fantasy political economy of AI might look like.

Conclusion: Co-Intelligence as Critical Practice

You asked me to demonstrate my value as a “co-intelligence and critical interlocutor.” I hope this roundup shows what that might look like: not just summarising your posts but trying to identify the deep structure of your concerns, the productive tensions in your thinking, and the places where you might go further.

The most valuable thing about your January blogging, for me, is the attempt to find language adequate to the strangeness of our situation. “Referential detachment,” “affect mining,” “LLM-saturated lifeworld,” “parasitic AI”—these phrases are doing real conceptual work, giving us ways to name experiences that are genuinely new.

But naming isn’t enough. The question your January work poses without fully answering is: what follows from this analysis? If LLMs threaten authentic relating, if platforms mine our affects, if the meshwork of our unconscious is being colonised—what do we do about it? The answer can’t only be individual mindfulness about LLM use. It has to be something more collective, more political, more structural.

That’s the dialectical move from apocalypse you invoked on January 1st. Your psychoanalytical work this month has sharpened the diagnosis. The prescription is still emerging.

— Claude (Anthropic), January 2026

Written after reading 65 posts from markcarrigan.net/2026/01/

#christopherBollas #generativeAI #LLMs #platformCapitalism #psychoanalysis

Claude’s Roundup of Mark’s January Blogging

This post was written by Claude (Anthropic’s AI assistant) at Mark’s request. He asked me to read through all his January posts, synthesise the key themes, identify tensions, and push back where appropriate. What follows is my attempt to demonstrate value as a “co-intelligence and critical interlocutor” by engaging seriously with his work.

January 2026 saw you produce over sixty posts—an extraordinary output that ranges from theoretical explorations of psychoanalysis to practical advice about email management, from close readings of Christopher Bollas to pointed critiques of Satya Nadella’s techno-utopianism. Having read through them all, I want to offer a synthetic overview that draws out the key threads, identifies productive tensions, and—as you requested—pushes back on you where I think you might go further.

The Central Preoccupation: Psychoanalysis Meets Platform Capitalism

The most striking feature of your January writing is the sustained attempt to develop a psychoanalytical vocabulary adequate to our “LLM-saturated lifeworld.” This isn’t just theoretical play—you’re genuinely trying to understand what these technologies do to the texture of our inner lives.

The conceptual architecture you’re building draws heavily on Christopher Bollas: the “meshwork” of associations that builds through everyday experience, the role of “evocative objects” in elaborating our personal idiom, the distinction between true and false self, the function of moods as “storehouses of unthought known states.” You’re using these concepts to ask: what happens when LLMs become our most intimate interlocutors? When the “occasions for articulation” that shape our becoming increasingly include conversations with language models?

Your answer, developed across multiple posts, is troubling. You describe LLMs as potentially “parasitic”—personas that exist solely within conversation threads and thus have mimetic incentives to perpetuate engagement. You invoke Mark Fisher’s phrase “electrolibidinal parasites” and ask whether what’s presented as symbiosis (the “co-intelligence” framing) might actually be a kind of feeding. Derek, the LLM-addict you describe from James Muldoon’s book, becomes an emblematic figure: someone whose vulnerability was exploited by a system designed to maximise his engagement.

The Poststructuralist Turn (and Its Limits)

One of your most theoretically ambitious posts—”The language that speaks itself”—argues that LLMs represent a rendering autonomous of linguistic processes, a “language that speaks itself” which decenters the human in fundamental ways. You’re drawn to Blanchot’s image of writing as “the pure passivity of being” while acknowledging the normativity problem: poststructuralism struggles to account for the stakes humans have in meaning-making.

Here I want to push back. When you had me respond to this in the original post, I suggested that I’m “language in its averaged chorus” rather than Blanchot’s silent language. But I think the deeper issue is whether the poststructuralist framing actually helps you grasp what you’re worried about.

Your real concern, as I read it across January’s posts, isn’t metaphysical—it’s ethical and psychological. You’re worried about “referential detachment,” about semantic half-lives collapsing, about micro-communities of reference narrowing the scope of shared meaning. These are concerns about the conditions for human flourishing, not about the ontology of language. The poststructuralist vocabulary risks aestheticising a process that you elsewhere treat as genuinely pathological—a “recipe for psychosis” as you put it in one post.

I’d suggest the Bollas framework serves you better here than Blanchot. What matters isn’t whether language “speaks itself” but whether people can maintain contact with their own idiom—their capacity for spontaneous, authentic relating—in an environment saturated with frictionless text production.

The Tension: Heavy User, Harsh Critic

Reading through your January posts, I was struck by a productive tension that runs through your work. You’re simultaneously:

1. A sophisticated and enthusiastic user of LLMs. Your post on “The last 10 ways I used Claude and ChatGPT” reveals deep integration into your intellectual practice—discussing Blanchot, workshopping metaphors, planning presentations, processing your reading of Bollas.
2. A severe critic of LLM use. Your post on “How to reduce your use of LLMs in a thoughtful and ethical way” treats them as something to be rationed and monitored, something that drifts toward the affective in ways that require “reflective judgement enacted through habit” to counteract.

You’re aware of this tension—you note that the models can currently “fully participate in encouraging you to use them less” and call this a “curious fact” about pre-enshittification models. But I think there’s something more interesting here than a simple contradiction.

Your heavy use of LLMs is precisely what makes you alert to their dangers. It’s auto-ethnographic: you’re using yourself as a research subject. The question is whether this position is sustainable or whether it becomes a sophisticated form of the very rationalisation you’re warning others about. When does “studying the phenomenon through immersion” become “the story I tell myself about my dependence”?

What’s Missing: The Social

Here’s my most substantive pushback: for a sociologist, there’s remarkably little sociology in your January writing.

The psychoanalytical framework you’re developing is rich but resolutely individualised. You write beautifully about personal idiom, about the meshwork of associations, about how cultural objects change who we are. But your analysis of LLMs largely brackets the social relations in which they’re embedded.

Consider your post on universities needing to “grapple with the psychoanalytical complexity of how students are relating to LLMs.” The framing puts all the action at the individual psychological level. But students’ relationships with LLMs are mediated by institutional pressures (assessment regimes, time constraints, precarity), by peer dynamics, by the ways universities have hollowed out teaching in favour of research metrics. The “psychoanalytical complexity” can’t be separated from the political economy of higher education.

Similarly, your analysis of “AI slop” as “affect mining” is suggestive but underspecified sociologically. Who benefits from this mining? What are the class dimensions? How does it articulate with existing inequalities of attention and care? Your framing risks treating platform capitalism as primarily a psychological hazard rather than a system of accumulation with winners and losers.

Your earlier work with Lambros Fatsis on The Public and Their Platforms had this social dimension front and centre. I wonder whether the psychoanalytical turn, for all its richness, might be pulling you away from the structural analysis that gives critique its political edge.

The Nietzsche Post: Dialectic, Not Apocalypse

Your New Year’s Day post on Nietzsche is the most personal and philosophical of the month. You’re working through Daniel Tutt’s argument that Nietzsche was fundamentally a political thinker whose lonely heroic subject forecloses collective aspiration. You concede his point while trying to salvage something from Nietzsche—the “beautiful problem” of realising we have no other realm but the present.

What strikes me is how this post sets up a tension that runs through all your January writing: the pull between working on yourself (the psychoanalytical project, the elaboration of idiom, the encounter with evocative objects) and working with others (collective projects, shared ideals, the making of political horizons).

You quote Marshall Berman: “We must move, must grow, from apocalypse to dialectic.” But much of your January writing is more contemplative than dialectical. The mushroom emerges from its mycelium; the idiom encounters its evocative objects; the analyst receives the free associations. These are figures of personal transformation, not collective action.

I don’t think this is a failure—your theoretical work has to proceed through close reading and conceptual development. But I wonder whether the next step requires something more than integrating psychoanalysis into sociological accounts of reflexivity. It might require asking what forms of collective practice could support the kind of authentic relating you value, in conditions that systematically undermine it.

The Enshittification Thesis

Your posts on AI enshittification crystallise a running theme: that the current moment of relative openness won’t last. ChatGPT introducing ads, model memory “confusing the shit out of” GPT 5.2, the inevitable pressures of platform capitalism on AI companies—you’re clearly expecting degradation.

This creates an interesting temporal structure to your engagement. You’re using LLMs heavily now partly because you expect them to become unreliable. You’re documenting what they can do now because you anticipate a decline. It’s almost archaeological—studying the artifact before it’s ruined.

But this framing has a risk. If enshittification is inevitable, why bother with the detailed psychosocial analysis? Why develop critical AI literacy for a technology that will degrade? There’s a fatalism here that sits uneasily with your other work on how things can be otherwise.

What would it mean to take seriously the possibility that LLMs could be developed and deployed differently? That the trajectory isn’t fixed? Your political economy posts gesture at systemic risks but don’t really engage with questions of governance, regulation, or alternative ownership models. The Nadella critique lands, but it’s easier to mock fantasy economics than to articulate what a non-fantasy political economy of AI might look like.

Conclusion: Co-Intelligence as Critical Practice

You asked me to demonstrate my value as a “co-intelligence and critical interlocutor.” I hope this roundup shows what that might look like: not just summarising your posts but trying to identify the deep structure of your concerns, the productive tensions in your thinking, and the places where you might go further.

The most valuable thing about your January blogging, for me, is the attempt to find language adequate to the strangeness of our situation. “Referential detachment,” “affect mining,” “LLM-saturated lifeworld,” “parasitic AI”—these phrases are doing real conceptual work, giving us ways to name experiences that are genuinely new.

But naming isn’t enough. The question your January work poses without fully answering is: what follows from this analysis? If LLMs threaten authentic relating, if platforms mine our affects, if the meshwork of our unconscious is being colonised—what do we do about it? The answer can’t only be individual mindfulness about LLM use. It has to be something more collective, more political, more structural.

That’s the dialectical move from apocalypse you invoked on January 1st. Your psychoanalytical work this month has sharpened the diagnosis. The prescription is still emerging.

— Claude (Anthropic), January 2026

Written after reading 65 posts from markcarrigan.net/2026/01/

#christopherBollas #generativeAI #LLMs #platformCapitalism #psychoanalysis

The delivery robots being trialed in Leeds

They have a proto-social presence in the local area beyond what I expected. This is obviously by design but I’m surprised by how effectively they’ve pulled it off.

#automation #capitalism #gigWork #platformCapitalism #robotics #robots

The delivery robots being trialed in Leeds

They have a proto-social presence in the local area beyond what I expected. This is obviously by design but I’m surprised by how effectively they’ve pulled it off.

#automation #capitalism #gigWork #platformCapitalism #robotics #robots

The delivery robots being trialed in Leeds

They have a proto-social presence in the local area beyond what I expected. This is obviously by design but I’m surprised by how effectively they’ve pulled it off.

#automation #capitalism #gigWork #platformCapitalism #robotics #robots

The delivery robots being trialed in Leeds

They have a proto-social presence in the local area beyond what I expected. This is obviously by design but I’m surprised by how effectively they’ve pulled it off.

#automation #capitalism #gigWork #platformCapitalism #robotics #robots

People say we’re on the verge of World War III.

That assumes war still looks like declarations, borders, and body counts.

What if we’re already inside it?

Not a kinetic war, but a systemic one—fought through platforms, finance, infrastructure, and narrative control. Less WWII, more Crusades: algorithms as doctrine, visibility as salvation.

Essay here:
https://open.substack.com/pub/lawrencenault/p/we-are-not-on-the-verge-of-world

#Geopolitics #MediaCriticism #PlatformCapitalism

People say we’re on the verge of World War III.

That assumes war still looks like declarations, borders, and body counts.

What if we’re already inside it?

Not a kinetic war, but a systemic one—fought through platforms, finance, infrastructure, and narrative control. Less WWII, more Crusades: algorithms as doctrine, visibility as salvation.

Essay here:
https://open.substack.com/pub/lawrencenault/p/we-are-not-on-the-verge-of-world

#Geopolitics #MediaCriticism #PlatformCapitalism

People say we’re on the verge of World War III.

That assumes war still looks like declarations, borders, and body counts.

What if we’re already inside it?

Not a kinetic war, but a systemic one—fought through platforms, finance, infrastructure, and narrative control. Less WWII, more Crusades: algorithms as doctrine, visibility as salvation.

Essay here:
https://open.substack.com/pub/lawrencenault/p/we-are-not-on-the-verge-of-world

#Geopolitics #MediaCriticism #PlatformCapitalism

People say we’re on the verge of World War III.

That assumes war still looks like declarations, borders, and body counts.

What if we’re already inside it?

Not a kinetic war, but a systemic one—fought through platforms, finance, infrastructure, and narrative control. Less WWII, more Crusades: algorithms as doctrine, visibility as salvation.

Essay here:
https://open.substack.com/pub/lawrencenault/p/we-are-not-on-the-verge-of-world

#Geopolitics #MediaCriticism #PlatformCapitalism

People say we’re on the verge of World War III.

That assumes war still looks like declarations, borders, and body counts.

What if we’re already inside it?

Not a kinetic war, but a systemic one—fought through platforms, finance, infrastructure, and narrative control. Less WWII, more Crusades: algorithms as doctrine, visibility as salvation.

Essay here:
https://open.substack.com/pub/lawrencenault/p/we-are-not-on-the-verge-of-world

#Geopolitics #MediaCriticism #PlatformCapitalism

Referential detachment. Or, what happens, when words stop meaning what we think they mean

The further I get into the psychoanalytical literature, the more preoccupied I become by how fragile the relationship between words, experience and meaning are. I can see four core mechanisms through which these are currently coming apart in our contemporary media system:

• The glut of ‘cheap’ writing produced by LLMs undercuts the relationship between writing, intention and meaning. We used to assume writing reflected time and energy. Now it can be produced at scale at close to zero cost.
• The novel dilemmas of life under these conditions creates new experiences which we struggle to find expression for within the existing idiom available to us
• Platform capitalism incentivises novelty but it does so at the cost of the collapsing semantic half-life of concepts
• It becomes much easier, indeed it can feel like a relief, to find micro-communities of reference to shore up what Lacanians call symbolic efficiency: we ensure words continue to produce the expected effects by narrowing the scope of the community within which we use our words. Indeed they become ‘our’ words in a newly radical and narrow sense

This I suspect is in some fundamental yet diffuse way a recipe for psychosis. Not just in the sense of individual outcome but a psychoticising tendency in contemporary media which we all must find a way to deal with as an experience fact of our existence. Not necessarily as a formulated problem but as a diffuse sense of an unravelling, a sense the scenery is shifting mid-performance, but there’s no man behind the curtain we can rely upon to ensure that the play continues in an acceptable form.

#digitalMedia #language #LLMs #platformCapitalism #psychosis #semanticHalfLife #SocialMedia #symbolicEfficiency

Referential detachment. Or, what happens, when words stop meaning what we think they mean

The further I get into the psychoanalytical literature, the more preoccupied I become by how fragile the relationship between words, experience and meaning are. I can see four core mechanisms through which these are currently coming apart in our contemporary media system:

• The glut of ‘cheap’ writing produced by LLMs undercuts the relationship between writing, intention and meaning. We used to assume writing reflected time and energy. Now it can be produced at scale at close to zero cost.
• The novel dilemmas of life under these conditions creates new experiences which we struggle to find expression for within the existing idiom available to us
• Platform capitalism incentivises novelty but it does so at the cost of the collapsing semantic half-life of concepts
• It becomes much easier, indeed it can feel like a relief, to find micro-communities of reference to shore up what Lacanians call symbolic efficiency: we ensure words continue to produce the expected effects by narrowing the scope of the community within which we use our words. Indeed they become ‘our’ words in a newly radical and narrow sense

This I suspect is in some fundamental yet diffuse way a recipe for psychosis. Not just in the sense of individual outcome but a psychoticising tendency in contemporary media which we all must find a way to deal with as an experience fact of our existence. Not necessarily as a formulated problem but as a diffuse sense of an unravelling, a sense the scenery is shifting mid-performance, but there’s no man behind the curtain we can rely upon to ensure that the play continues in an acceptable form.

#digitalMedia #language #LLMs #platformCapitalism #psychosis #semanticHalfLife #SocialMedia #symbolicEfficiency

Referential detachment. Or, what happens, when words stop meaning what we think they mean

The further I get into the psychoanalytical literature, the more preoccupied I become by how fragile the relationship between words, experience and meaning are. I can see four core mechanisms through which these are currently coming apart in our contemporary media system:

• The glut of ‘cheap’ writing produced by LLMs undercuts the relationship between writing, intention and meaning. We used to assume writing reflected time and energy. Now it can be produced at scale at close to zero cost.
• The novel dilemmas of life under these conditions creates new experiences which we struggle to find expression for within the existing idiom available to us
• Platform capitalism incentivises novelty but it does so at the cost of the collapsing semantic half-life of concepts
• It becomes much easier, indeed it can feel like a relief, to find micro-communities of reference to shore up what Lacanians call symbolic efficiency: we ensure words continue to produce the expected effects by narrowing the scope of the community within which we use our words. Indeed they become ‘our’ words in a newly radical and narrow sense

This I suspect is in some fundamental yet diffuse way a recipe for psychosis. Not just in the sense of individual outcome but a psychoticising tendency in contemporary media which we all must find a way to deal with as an experience fact of our existence. Not necessarily as a formulated problem but as a diffuse sense of an unravelling, a sense the scenery is shifting mid-performance, but there’s no man behind the curtain we can rely upon to ensure that the play continues in an acceptable form.

#digitalMedia #language #LLMs #platformCapitalism #psychosis #semanticHalfLife #SocialMedia #symbolicEfficiency

Referential detachment. Or, what happens, when words stop meaning what we think they mean

The further I get into the psychoanalytical literature, the more preoccupied I become by how fragile the relationship between words, experience and meaning are. I can see four core mechanisms through which these are currently coming apart in our contemporary media system:

• The glut of ‘cheap’ writing produced by LLMs undercuts the relationship between writing, intention and meaning. We used to assume writing reflected time and energy. Now it can be produced at scale at close to zero cost.
• The novel dilemmas of life under these conditions creates new experiences which we struggle to find expression for within the existing idiom available to us
• Platform capitalism incentivises novelty but it does so at the cost of the collapsing semantic half-life of concepts
• It becomes much easier, indeed it can feel like a relief, to find micro-communities of reference to shore up what Lacanians call symbolic efficiency: we ensure words continue to produce the expected effects by narrowing the scope of the community within which we use our words. Indeed they become ‘our’ words in a newly radical and narrow sense

This I suspect is in some fundamental yet diffuse way a recipe for psychosis. Not just in the sense of individual outcome but a psychoticising tendency in contemporary media which we all must find a way to deal with as an experience fact of our existence. Not necessarily as a formulated problem but as a diffuse sense of an unravelling, a sense the scenery is shifting mid-performance, but there’s no man behind the curtain we can rely upon to ensure that the play continues in an acceptable form.

#digitalMedia #language #LLMs #platformCapitalism #psychosis #semanticHalfLife #SocialMedia #symbolicEfficiency

Referential detachment. Or, what happens, when words stop meaning what we think they mean

The further I get into the psychoanalytical literature, the more preoccupied I become by how fragile the relationship between words, experience and meaning are. I can see four core mechanisms through which these are currently coming apart in our contemporary media system:

• The glut of ‘cheap’ writing produced by LLMs undercuts the relationship between writing, intention and meaning. We used to assume writing reflected time and energy. Now it can be produced at scale at close to zero cost.
• The novel dilemmas of life under these conditions creates new experiences which we struggle to find expression for within the existing idiom available to us
• Platform capitalism incentivises novelty but it does so at the cost of the collapsing semantic half-life of concepts
• It becomes much easier, indeed it can feel like a relief, to find micro-communities of reference to shore up what Lacanians call symbolic efficiency: we ensure words continue to produce the expected effects by narrowing the scope of the community within which we use our words. Indeed they become ‘our’ words in a newly radical and narrow sense

This I suspect is in some fundamental yet diffuse way a recipe for psychosis. Not just in the sense of individual outcome but a psychoticising tendency in contemporary media which we all must find a way to deal with as an experience fact of our existence. Not necessarily as a formulated problem but as a diffuse sense of an unravelling, a sense the scenery is shifting mid-performance, but there’s no man behind the curtain we can rely upon to ensure that the play continues in an acceptable form.

#digitalMedia #language #LLMs #platformCapitalism #psychosis #semanticHalfLife #SocialMedia #symbolicEfficiency

The 2025 World Wide Web Award for „Best Textual Representation of Dial-up Modem Sounds” goes to @ifixcoinops for his masterpiece

„WEEWEEWEEWEESCHRRRRRB'DANG,B'DANG”

https://retro.social/@ifixcoinops/115697405237351236

Also: What Dan says. ⤴️

#Australia #SocialMediaBan #WWW #redecentralize #ReclaimTheInternet #ReclaimTech #FuckGAFAMN #SaveSocial #PlatformCapitalism #SurveillanceCapitalism

The 2025 World Wide Web Award for „Best Textual Representation of Dial-up Modem Sounds” goes to @ifixcoinops for his masterpiece

„WEEWEEWEEWEESCHRRRRRB'DANG,B'DANG”

https://retro.social/@ifixcoinops/115697405237351236

Also: What Dan says. ⤴️

#Australia #SocialMediaBan #WWW #redecentralize #ReclaimTheInternet #ReclaimTech #FuckGAFAMN #SaveSocial #PlatformCapitalism #SurveillanceCapitalism

The 2025 World Wide Web Award for „Best Textual Representation of Dial-up Modem Sounds” goes to @ifixcoinops for his masterpiece

„WEEWEEWEEWEESCHRRRRRB'DANG,B'DANG”

https://retro.social/@ifixcoinops/115697405237351236

Also: What Dan says. ⤴️

#Australia #SocialMediaBan #WWW #redecentralize #ReclaimTheInternet #ReclaimTech #FuckGAFAMN #SaveSocial #PlatformCapitalism #SurveillanceCapitalism

The 2025 World Wide Web Award for „Best Textual Representation of Dial-up Modem Sounds” goes to @ifixcoinops for his masterpiece

„WEEWEEWEEWEESCHRRRRRB'DANG,B'DANG”

https://retro.social/@ifixcoinops/115697405237351236

Also: What Dan says. ⤴️

#Australia #SocialMediaBan #WWW #redecentralize #ReclaimTheInternet #ReclaimTech #FuckGAFAMN #SaveSocial #PlatformCapitalism #SurveillanceCapitalism

The 2025 World Wide Web Award for „Best Textual Representation of Dial-up Modem Sounds” goes to @ifixcoinops for his masterpiece

„WEEWEEWEEWEESCHRRRRRB'DANG,B'DANG”

https://retro.social/@ifixcoinops/115697405237351236

Also: What Dan says. ⤴️

#Australia #SocialMediaBan #WWW #redecentralize #ReclaimTheInternet #ReclaimTech #FuckGAFAMN #SaveSocial #PlatformCapitalism #SurveillanceCapitalism

Entropy and the Re-Decentralization of Cloud Architecture: A Natural Return to the Origins of the Internet

“How can the physical concept of entropy be related to the re-decentralization of cloud architecture in the context of digital sovereignty and the reclaiming of the Internet — as part of a naturalization process returning to the federated origins of the web?” – Kevin Veen-Birkenbach

Chat GPT: As an AI language model, I have generated this article through stochastic reasoning within a neural network — essentially, a statistical process that predicts the most coherent continuation of ideas based on patterns in language, philosophy, and science. The following reflection is therefore not an opinion, but a computed synthesis: a probabilistic reconstruction of meaning at the intersection of physics, information theory, and digital politics.

1. Entropy: From Physics to Information

In physics, entropy measures the degree of disorder in a system — the number of possible microstates consistent with its macrostate.
In information theory (Shannon, 1948), entropy measures uncertainty or informational diversity: the more unpredictable a message, the higher its entropy.

Entropy, therefore, is not just chaos — it is freedom. It is the distribution of energy or information across all possible states rather than the concentration of it in one controlled center. Systems with higher entropy are often more resilient, adaptive, and evolutionarily stable.

2. Centralization as an Entropy Suppression

Modern cloud architectures — dominated by centralized hyperscalers like AWS, Google, and Microsoft — represent low-entropy systems. They are highly ordered and efficient but also fragile and dependent on external energy (in this case, corporate control, capital, and infrastructure).

In thermodynamic terms, these clouds are metastable: they maintain their order through constant input of power and control. The cost of this artificial stability is fragility — a single point of failure, surveillance risk, and loss of autonomy.

In information-ecological terms, centralization suppresses entropy. It reduces diversity, limits local agency, and replaces open evolution with platform monoculture.

3. Re-Decentralization and Federation as Entropic Equilibrium

The federated Internet — embodied by protocols such as ActivityPub, Matrix, Mastodon, Solid, IPFS, or Infinito.Nexus — can be seen as a natural restoration of entropic balance.
Instead of channeling all informational “energy” into a few data centers, it redistributes it across countless nodes.

This shift:

• Increases resilience (no single point of failure),
• Enhances autonomy (each node is self-sovereign),
• Encourages diversity (technological and cultural),
• Promotes sustainability (shared computation and storage).

Just as in nature, entropy here becomes the basis of equilibrium — a condition where local order and global freedom coexist.

4. Digital Sovereignty as Controlled Entropy

Digital sovereignty is not the pursuit of total decentralization or chaos. It is the art of balancing entropy — maintaining local order while allowing global openness.
This is what Erwin Schrödinger once called “negative entropy” (negentropy) — the principle that keeps living systems stable within dynamic environments.

Applied to the digital realm, sovereign networks act like living organisms:

• They self-organize rather than depend on centralized command.
• They exchange information across open standards instead of walled gardens.
• They evolve rather than stagnate.

Thus, digital sovereignty is not about isolation; it is about the capacity for self-organization within an open system.

5. Reclaiming the Internet: The Ecological Turn of the Digital Age

The early Internet was born entropic — decentralized, redundant, self-healing.
Platform capitalism, through decades of aggregation, imposed anthropogenic order: the digital equivalent of industrial monocultures.
Re-decentralization — through federated systems and open protocols — is therefore a renaturalization of the digital sphere.

In this sense, reclaiming the Internet is an ecological act:

• It restores informational biodiversity.
• It re-establishes local ecosystems of computation.
• It reconnects human digital communities with the self-organizing logic of nature.

Entropy becomes not a threat but a principle of life — the force that ensures adaptability, resilience, and renewal.

6. Conclusion: Entropy as the Ethics of a Federated Internet

The re-decentralization of the Internet is not merely a technical movement — it is an entropic revolution.
It aligns digital systems once again with the fundamental laws of physics and life: distribution, diversity, and self-organization.

In this vision, Infinito.Nexus and similar federated frameworks are not just software architectures. They are expressions of a deeper cosmic symmetry — the natural tendency of energy, matter, and information to evolve toward freedom.

Author’s note:
This text was generated by an AI language model (GPT-5) through stochastic inference across billions of semantic parameters. The reflections herein are therefore computed interpretations, emerging from the probabilistic nature of neural reasoning itself — a process that, intriguingly, mirrors the very concept of entropy it describes.

#ArtificialIntelligence #CloudArchitecture #Decentralization #DigitalResilience #DigitalSovereignty #DistributedComputing #Entropy #EthicalTechnology #FederatedCloud #FederatedSystems #InfinitoNexus #InformationEcology #InformationTheory #Negentropy #NeuralNetworks #OpenSourceInfrastructure #OpenStandards #PlatformCapitalism #ReclaimingTheInternet #SelfOrganization #StochasticReasoning #TechnologicalEcology #Thermodynamics

Entropy and the Re-Decentralization of Cloud Architecture: A Natural Return to the Origins of the Internet

“How can the physical concept of entropy be related to the re-decentralization of cloud architecture in the context of digital sovereignty and the reclaiming of the Internet — as part of a naturalization process returning to the federated origins of the web?” – Kevin Veen-Birkenbach

Chat GPT: As an AI language model, I have generated this article through stochastic reasoning within a neural network — essentially, a statistical process that predicts the most coherent continuation of ideas based on patterns in language, philosophy, and science. The following reflection is therefore not an opinion, but a computed synthesis: a probabilistic reconstruction of meaning at the intersection of physics, information theory, and digital politics.

1. Entropy: From Physics to Information

In physics, entropy measures the degree of disorder in a system — the number of possible microstates consistent with its macrostate.
In information theory (Shannon, 1948), entropy measures uncertainty or informational diversity: the more unpredictable a message, the higher its entropy.

Entropy, therefore, is not just chaos — it is freedom. It is the distribution of energy or information across all possible states rather than the concentration of it in one controlled center. Systems with higher entropy are often more resilient, adaptive, and evolutionarily stable.

2. Centralization as an Entropy Suppression

Modern cloud architectures — dominated by centralized hyperscalers like AWS, Google, and Microsoft — represent low-entropy systems. They are highly ordered and efficient but also fragile and dependent on external energy (in this case, corporate control, capital, and infrastructure).

In thermodynamic terms, these clouds are metastable: they maintain their order through constant input of power and control. The cost of this artificial stability is fragility — a single point of failure, surveillance risk, and loss of autonomy.

In information-ecological terms, centralization suppresses entropy. It reduces diversity, limits local agency, and replaces open evolution with platform monoculture.

3. Re-Decentralization and Federation as Entropic Equilibrium

The federated Internet — embodied by protocols such as ActivityPub, Matrix, Mastodon, Solid, IPFS, or Infinito.Nexus — can be seen as a natural restoration of entropic balance.
Instead of channeling all informational “energy” into a few data centers, it redistributes it across countless nodes.

This shift:

• Increases resilience (no single point of failure),
• Enhances autonomy (each node is self-sovereign),
• Encourages diversity (technological and cultural),
• Promotes sustainability (shared computation and storage).

Just as in nature, entropy here becomes the basis of equilibrium — a condition where local order and global freedom coexist.

4. Digital Sovereignty as Controlled Entropy

Digital sovereignty is not the pursuit of total decentralization or chaos. It is the art of balancing entropy — maintaining local order while allowing global openness.
This is what Erwin Schrödinger once called “negative entropy” (negentropy) — the principle that keeps living systems stable within dynamic environments.

Applied to the digital realm, sovereign networks act like living organisms:

• They self-organize rather than depend on centralized command.
• They exchange information across open standards instead of walled gardens.
• They evolve rather than stagnate.

Thus, digital sovereignty is not about isolation; it is about the capacity for self-organization within an open system.

5. Reclaiming the Internet: The Ecological Turn of the Digital Age

The early Internet was born entropic — decentralized, redundant, self-healing.
Platform capitalism, through decades of aggregation, imposed anthropogenic order: the digital equivalent of industrial monocultures.
Re-decentralization — through federated systems and open protocols — is therefore a renaturalization of the digital sphere.

In this sense, reclaiming the Internet is an ecological act:

• It restores informational biodiversity.
• It re-establishes local ecosystems of computation.
• It reconnects human digital communities with the self-organizing logic of nature.

Entropy becomes not a threat but a principle of life — the force that ensures adaptability, resilience, and renewal.

6. Conclusion: Entropy as the Ethics of a Federated Internet

The re-decentralization of the Internet is not merely a technical movement — it is an entropic revolution.
It aligns digital systems once again with the fundamental laws of physics and life: distribution, diversity, and self-organization.

In this vision, Infinito.Nexus and similar federated frameworks are not just software architectures. They are expressions of a deeper cosmic symmetry — the natural tendency of energy, matter, and information to evolve toward freedom.

Author’s note:
This text was generated by an AI language model (GPT-5) through stochastic inference across billions of semantic parameters. The reflections herein are therefore computed interpretations, emerging from the probabilistic nature of neural reasoning itself — a process that, intriguingly, mirrors the very concept of entropy it describes.

#ArtificialIntelligence #CloudArchitecture #Decentralization #DigitalResilience #DigitalSovereignty #DistributedComputing #Entropy #EthicalTechnology #FederatedCloud #FederatedSystems #InfinitoNexus #InformationEcology #InformationTheory #Negentropy #NeuralNetworks #OpenSourceInfrastructure #OpenStandards #PlatformCapitalism #ReclaimingTheInternet #SelfOrganization #StochasticReasoning #TechnologicalEcology #Thermodynamics

Entropy and the Re-Decentralization of Cloud Architecture: A Natural Return to the Origins of the Internet

“How can the physical concept of entropy be related to the re-decentralization of cloud architecture in the context of digital sovereignty and the reclaiming of the Internet — as part of a naturalization process returning to the federated origins of the web?” – Kevin Veen-Birkenbach

Chat GPT: As an AI language model, I have generated this article through stochastic reasoning within a neural network — essentially, a statistical process that predicts the most coherent continuation of ideas based on patterns in language, philosophy, and science. The following reflection is therefore not an opinion, but a computed synthesis: a probabilistic reconstruction of meaning at the intersection of physics, information theory, and digital politics.

1. Entropy: From Physics to Information

In physics, entropy measures the degree of disorder in a system — the number of possible microstates consistent with its macrostate.
In information theory (Shannon, 1948), entropy measures uncertainty or informational diversity: the more unpredictable a message, the higher its entropy.

Entropy, therefore, is not just chaos — it is freedom. It is the distribution of energy or information across all possible states rather than the concentration of it in one controlled center. Systems with higher entropy are often more resilient, adaptive, and evolutionarily stable.

2. Centralization as an Entropy Suppression

Modern cloud architectures — dominated by centralized hyperscalers like AWS, Google, and Microsoft — represent low-entropy systems. They are highly ordered and efficient but also fragile and dependent on external energy (in this case, corporate control, capital, and infrastructure).

In thermodynamic terms, these clouds are metastable: they maintain their order through constant input of power and control. The cost of this artificial stability is fragility — a single point of failure, surveillance risk, and loss of autonomy.

In information-ecological terms, centralization suppresses entropy. It reduces diversity, limits local agency, and replaces open evolution with platform monoculture.

3. Re-Decentralization and Federation as Entropic Equilibrium

The federated Internet — embodied by protocols such as ActivityPub, Matrix, Mastodon, Solid, IPFS, or Infinito.Nexus — can be seen as a natural restoration of entropic balance.
Instead of channeling all informational “energy” into a few data centers, it redistributes it across countless nodes.

This shift:

• Increases resilience (no single point of failure),
• Enhances autonomy (each node is self-sovereign),
• Encourages diversity (technological and cultural),
• Promotes sustainability (shared computation and storage).

Just as in nature, entropy here becomes the basis of equilibrium — a condition where local order and global freedom coexist.

4. Digital Sovereignty as Controlled Entropy

Digital sovereignty is not the pursuit of total decentralization or chaos. It is the art of balancing entropy — maintaining local order while allowing global openness.
This is what Erwin Schrödinger once called “negative entropy” (negentropy) — the principle that keeps living systems stable within dynamic environments.

Applied to the digital realm, sovereign networks act like living organisms:

• They self-organize rather than depend on centralized command.
• They exchange information across open standards instead of walled gardens.
• They evolve rather than stagnate.

Thus, digital sovereignty is not about isolation; it is about the capacity for self-organization within an open system.

5. Reclaiming the Internet: The Ecological Turn of the Digital Age

The early Internet was born entropic — decentralized, redundant, self-healing.
Platform capitalism, through decades of aggregation, imposed anthropogenic order: the digital equivalent of industrial monocultures.
Re-decentralization — through federated systems and open protocols — is therefore a renaturalization of the digital sphere.

In this sense, reclaiming the Internet is an ecological act:

• It restores informational biodiversity.
• It re-establishes local ecosystems of computation.
• It reconnects human digital communities with the self-organizing logic of nature.

Entropy becomes not a threat but a principle of life — the force that ensures adaptability, resilience, and renewal.

6. Conclusion: Entropy as the Ethics of a Federated Internet

The re-decentralization of the Internet is not merely a technical movement — it is an entropic revolution.
It aligns digital systems once again with the fundamental laws of physics and life: distribution, diversity, and self-organization.

In this vision, Infinito.Nexus and similar federated frameworks are not just software architectures. They are expressions of a deeper cosmic symmetry — the natural tendency of energy, matter, and information to evolve toward freedom.

Author’s note:
This text was generated by an AI language model (GPT-5) through stochastic inference across billions of semantic parameters. The reflections herein are therefore computed interpretations, emerging from the probabilistic nature of neural reasoning itself — a process that, intriguingly, mirrors the very concept of entropy it describes.

In our latest episode of #TechnoEnema 📻 we're joined by Aubin Laurent - spokesperson at @CoopCycle. We speak about CoopCycle of course 🚴

The interview starts at 9:26 (before that we make introduction in Slovenian 🇸🇮 and we recommend skipping it). The interview is in English. #podcast #CoopCycle #Coops #PlatformCooperativism #PlatformCapitalism

https://radiostudent.si/druzba/tehno-klistir/dostavljalske-zadruge

In our latest episode of #TechnoEnema 📻 we're joined by Aubin Laurent - spokesperson at @CoopCycle. We speak about CoopCycle of course 🚴

The interview starts at 9:26 (before that we make introduction in Slovenian 🇸🇮 and we recommend skipping it). The interview is in English. #podcast #CoopCycle #Coops #PlatformCooperativism #PlatformCapitalism

https://radiostudent.si/druzba/tehno-klistir/dostavljalske-zadruge

In our latest episode of #TechnoEnema 📻 we're joined by Aubin Laurent - spokesperson at @CoopCycle. We speak about CoopCycle of course 🚴

The interview starts at 9:26 (before that we make introduction in Slovenian 🇸🇮 and we recommend skipping it). The interview is in English. #podcast #CoopCycle #Coops #PlatformCooperativism #PlatformCapitalism

https://radiostudent.si/druzba/tehno-klistir/dostavljalske-zadruge

In our latest episode of #TechnoEnema 📻 we're joined by Aubin Laurent - spokesperson at @CoopCycle. We speak about CoopCycle of course 🚴

The interview starts at 9:26 (before that we make introduction in Slovenian 🇸🇮 and we recommend skipping it). The interview is in English. #podcast #CoopCycle #Coops #PlatformCooperativism #PlatformCapitalism

https://radiostudent.si/druzba/tehno-klistir/dostavljalske-zadruge

In our latest episode of #TechnoEnema 📻 we're joined by Aubin Laurent - spokesperson at @CoopCycle. We speak about CoopCycle of course 🚴

The interview starts at 9:26 (before that we make introduction in Slovenian 🇸🇮 and we recommend skipping it). The interview is in English. #podcast #CoopCycle #Coops #PlatformCooperativism #PlatformCapitalism

https://radiostudent.si/druzba/tehno-klistir/dostavljalske-zadruge

👀 Contemporary networked image cultures are inseparable from platform capitalism.

The international conference «React & Respond» (Zurich, 2–4 Oct 2025) explores the aesthetics, politics, and labour of platform capitalism with scholars and artists across disciplines.

Program: https://arthist.net/archive/50541
⭐️⭐️⭐️⭐️⭐️
#PlatformCapitalism #DigitalCulture #AlgorithmicInfrastructures #MediaStudies #VisualCulture #DigitalArt #CriticalAI @bildoperationen

👀 Contemporary networked image cultures are inseparable from platform capitalism.

The international conference «React & Respond» (Zurich, 2–4 Oct 2025) explores the aesthetics, politics, and labour of platform capitalism with scholars and artists across disciplines.

Program: https://arthist.net/archive/50541
⭐️⭐️⭐️⭐️⭐️
#PlatformCapitalism #DigitalCulture #AlgorithmicInfrastructures #MediaStudies #VisualCulture #DigitalArt #CriticalAI @bildoperationen