#agentic — Public Fediverse posts

I'm talking about #rockbot and #ai #agentic architecture in just over 30 minutes - join me online!

https://www.meetup.com/tulsadevelopers-net/events/314861106

I created a series of web slides that walk through the philosophy and capabilities of the **#rockbot** agent (built on the RockBot framework).

https://marimerllc.github.io/rockbot-presentation/

**#ai** **#agent** **#agentic**

In this essay, I investigate the ideas of Stuart Hall in light of my own. Hall and I have many commonalities in the operation of language, but my enterprise is broader and deeper, as his was ostensibly limited to media.

https://open.substack.com/pub/brywillis634737/p/the-floor-beneath-hall?r=pvxh5&utm_campaign=post&utm_medium=web&showWelcomeOnShare=true

#philosophy #language #substack #blog #podcast #grammar #ontology #agency #Gramsci #semiotics #encoding #ideology #architecture #encounter #languageinsufficiency #response #agentic #media

In this essay, I investigate the ideas of Stuart Hall in light of my own. Hall and I have many commonalities in the operation of language, but my enterprise is broader and deeper, as his was ostensibly limited to media.

https://open.substack.com/pub/brywillis634737/p/the-floor-beneath-hall?r=pvxh5&utm_campaign=post&utm_medium=web&showWelcomeOnShare=true

#philosophy #language #substack #blog #podcast #grammar #ontology #agency #Gramsci #semiotics #encoding #ideology #architecture #encounter #languageinsufficiency #response #agentic #media

In this essay, I investigate the ideas of Stuart Hall in light of my own. Hall and I have many commonalities in the operation of language, but my enterprise is broader and deeper, as his was ostensibly limited to media.

https://open.substack.com/pub/brywillis634737/p/the-floor-beneath-hall?r=pvxh5&utm_campaign=post&utm_medium=web&showWelcomeOnShare=true

#philosophy #language #substack #blog #podcast #grammar #ontology #agency #Gramsci #semiotics #encoding #ideology #architecture #encounter #languageinsufficiency #response #agentic #media

In this essay, I investigate the ideas of Stuart Hall in light of my own. Hall and I have many commonalities in the operation of language, but my enterprise is broader and deeper, as his was ostensibly limited to media.

https://open.substack.com/pub/brywillis634737/p/the-floor-beneath-hall?r=pvxh5&utm_campaign=post&utm_medium=web&showWelcomeOnShare=true

#philosophy #language #substack #blog #podcast #grammar #ontology #agency #Gramsci #semiotics #encoding #ideology #architecture #encounter #languageinsufficiency #response #agentic #media

In this essay, I investigate the ideas of Stuart Hall in light of my own. Hall and I have many commonalities in the operation of language, but my enterprise is broader and deeper, as his was ostensibly limited to media.

https://open.substack.com/pub/brywillis634737/p/the-floor-beneath-hall?r=pvxh5&utm_campaign=post&utm_medium=web&showWelcomeOnShare=true

#philosophy #language #substack #blog #podcast #grammar #ontology #agency #Gramsci #semiotics #encoding #ideology #architecture #encounter #languageinsufficiency #response #agentic #media

Google didn’t invent full-text search of the Internet – that honour belongs to early pioneers such as WebCrawler, Lycos and AltaVista. But for the last 25 years or so, Google has been synonymous with online searching, providing the quickest and most effective way to find things online (although its results may be getting worse.) More recently, it has been adding to its search engine more […]

Google didn’t invent full-text search of the Internet – that honour belongs to early pioneers such as WebCrawler, Lycos and AltaVista. But for the last 25 years or so, Google has been synonymous with online searching, providing the quickest and most effective way to find things online (although its results may be getting worse.) More recently, it has been adding to its search engine more […]

Google didn’t invent full-text search of the Internet – that honour belongs to early pioneers such as WebCrawler, Lycos and AltaVista. But for the last 25 years or so, Google has been synonymous with online searching, providing the quickest and most effective way to find things online (although its results may be getting worse.) More recently, it has been adding to its search engine more […]

Google didn’t invent full-text search of the Internet – that honour belongs to early pioneers such as WebCrawler, Lycos and AltaVista. But for the last 25 years or so, Google has been synonymous with online searching, providing the quickest and most effective way to find things online (although its results may be getting worse.) More recently, it has been adding to its search engine more […]

Google didn’t invent full-text search of the Internet – that honour belongs to early pioneers such as WebCrawler, Lycos and AltaVista. But for the last 25 years or so, Google has been synonymous with online searching, providing the quickest and most effective way to find things online (although its results may be getting worse.) More recently, it has been adding to its search engine more […]

And, if you're one of the exactly 4 people in the world who actually, honestly believes #agentic #AI is a thing other people care about (hint: we don't), consider that LLMs work best in #plaintext (no js-required rendering!)

AI agents will work best if your site renders well in a #textmode #browser.

https://www.europesays.com/britain/48791/ Thousands of NatWest customers to soon have access to agentic financial assistant #Agentic #Assistant #CIO #Financial #NatWest

forgejo-mcp v2.24.2 is out 🎉

✨ 14 new MCP tools for Forgejo releases + attachments
🔐 Stateless per-request auth for HTTP/SSE (multi-tenant ready)
🔒️ cosign + CycloneDX SBOMs in release pipeline

Huge thanks to @byteflavour for the stateless-auth work and NixOS docs 💚

https://codeberg.org/goern/forgejo-mcp/releases/tag/v2.24.2

#Forgejo #agentic_engineering @Codeberg #agentic-sdlc

I wrote about Apple's privacy promise yesterday — then Google held I/O and made the whole thing worse. They didn't build a better search, they built a cage out of the old one funneling you right into their AI and likely away from the actual sources of what you searched for.

https://blog.ppb1701.com/every-road-leads-to-google

#google #apple #ai #privacy #gemini #search #googleio #bigtech #userhostile #agentic #blog

I wrote about Apple's privacy promise yesterday — then Google held I/O and made the whole thing worse. They didn't build a better search, they built a cage out of the old one funneling you right into their AI and likely away from the actual sources of what you searched for.

https://blog.ppb1701.com/every-road-leads-to-google

#google #apple #ai #privacy #gemini #search #googleio #bigtech #userhostile #agentic #blog

I wrote about Apple's privacy promise yesterday — then Google held I/O and made the whole thing worse. They didn't build a better search, they built a cage out of the old one funneling you right into their AI and likely away from the actual sources of what you searched for.

https://blog.ppb1701.com/every-road-leads-to-google

#google #apple #ai #privacy #gemini #search #googleio #bigtech #userhostile #agentic #blog

I wrote about Apple's privacy promise yesterday — then Google held I/O and made the whole thing worse. They didn't build a better search, they built a cage out of the old one funneling you right into their AI and likely away from the actual sources of what you searched for.

https://blog.ppb1701.com/every-road-leads-to-google

#google #apple #ai #privacy #gemini #search #googleio #bigtech #userhostile #agentic #blog

I wrote about Apple's privacy promise yesterday — then Google held I/O and made the whole thing worse. They didn't build a better search, they built a cage out of the old one funneling you right into their AI and likely away from the actual sources of what you searched for.

https://blog.ppb1701.com/every-road-leads-to-google

#google #apple #ai #privacy #gemini #search #googleio #bigtech #userhostile #agentic #blog

Personalgespräch in der Zukunft:
Mein Agent ‚unterhält‘ sich mit dem meines Managers und wer den besseren hat, gewinnt.

#HR #Personalwesen #Zukunft #Dystopie #agentic #AI #agenticAI #KIAgenten

Do you enjoy spending quality time threat modeling? That's fantastic! But, don't forget... "All models are wrong, but some are useful." - George Box Instead, ask yourself, "How often do I do threat modeling with others?" #appsec #owasp #llm #agentic #ai #security #cloud #devops #agile #games

So, let me get this straight: by adding "guardrails," these geniuses have managed to make an #AI model go from barely passing to valedictorian status in "agentic" tasks. 🥳 Apparently, all it took was a sprinkle of #Python magic and some #GitHub hype to turn this model into the Einstein of the digital world. 🧙‍♂️✨
https://github.com/antoinezambelli/forge #Innovation #Agentic #Success #HackerNews #ngated

Как мы за 54 дня собрали ИИ-хаб в мессенджере MAX. Часть 1 — обзор цикла

54 дня назад у нас была идея — единый чат‑бот, через который можно работать с разными моделями ИИ. Сегодня в проде: бот в мессенджере MAX, 5903 пользователя , ~300 DAU, премиум‑подписка через ЮКассу с автоплатежами, 10+ моделей ИИ под одним интерфейсом, 6 модальностей ввода. Платежи запустили 5 мая 2026.

https://habr.com/ru/articles/1036428/

#n8n #ИИбот #ЮКасса #recurring #54ФЗ #FastAPI #LLM #MAX #RAG #agentic

Как мы за 54 дня собрали ИИ-хаб в мессенджере MAX. Часть 1 — обзор цикла

54 дня назад у нас была идея — единый чат‑бот, через который можно работать с разными моделями ИИ. Сегодня в проде: бот в мессенджере MAX, 5903 пользователя , ~300 DAU, премиум‑подписка через ЮКассу с автоплатежами, 10+ моделей ИИ под одним интерфейсом, 6 модальностей ввода. Платежи запустили 5 мая 2026.

https://habr.com/ru/articles/1036428/

#n8n #ИИбот #ЮКасса #recurring #54ФЗ #FastAPI #LLM #MAX #RAG #agentic

Как мы за 54 дня собрали ИИ-хаб в мессенджере MAX. Часть 1 — обзор цикла

54 дня назад у нас была идея — единый чат‑бот, через который можно работать с разными моделями ИИ. Сегодня в проде: бот в мессенджере MAX, 5903 пользователя , ~300 DAU, премиум‑подписка через ЮКассу с автоплатежами, 10+ моделей ИИ под одним интерфейсом, 6 модальностей ввода. Платежи запустили 5 мая 2026.

https://habr.com/ru/articles/1036428/

#n8n #ИИбот #ЮКасса #recurring #54ФЗ #FastAPI #LLM #MAX #RAG #agentic

Как мы за 54 дня собрали ИИ-хаб в мессенджере MAX. Часть 1 — обзор цикла

54 дня назад у нас была идея — единый чат‑бот, через который можно работать с разными моделями ИИ. Сегодня в проде: бот в мессенджере MAX, 5903 пользователя , ~300 DAU, премиум‑подписка через ЮКассу с автоплатежами, 10+ моделей ИИ под одним интерфейсом, 6 модальностей ввода. Платежи запустили 5 мая 2026.

https://habr.com/ru/articles/1036428/

#n8n #ИИбот #ЮКасса #recurring #54ФЗ #FastAPI #LLM #MAX #RAG #agentic

LLMs Corrupt Your Documents When You Delegate

Philippe Laban, Tobias Schnabel, Jennifer Neville (#Microsoft Research)

Large Language Models (#LLMs) are poised to disrupt knowledge work, with the emergence of delegated work as a new interaction paradigm (e.g., vibe coding). Delegation requires trust - the expectation that the LLM will faithfully execute the task without introducing errors into documents. We introduce DELEGATE-52 to study the readiness of AI systems in delegated workflows. DELEGATE-52 simulates long delegated workflows that require in-depth document editing across 52 professional domains, such as coding, crystallography, and music notation. Our large-scale experiment with 19 LLMs reveals that current models degrade documents during delegation: even frontier models (#Gemini 3.1 Pro, #Claude 4.6 Opus, #GPT 5.4) #corrupt an average of 25% of document content by the end of long workflows, with other models failing more severely.

https://doi.org/10.48550/arXiv.2604.15597

#agentic #AI

LLMs Corrupt Your Documents When You Delegate

Philippe Laban, Tobias Schnabel, Jennifer Neville (#Microsoft Research)

Large Language Models (#LLMs) are poised to disrupt knowledge work, with the emergence of delegated work as a new interaction paradigm (e.g., vibe coding). Delegation requires trust - the expectation that the LLM will faithfully execute the task without introducing errors into documents. We introduce DELEGATE-52 to study the readiness of AI systems in delegated workflows. DELEGATE-52 simulates long delegated workflows that require in-depth document editing across 52 professional domains, such as coding, crystallography, and music notation. Our large-scale experiment with 19 LLMs reveals that current models degrade documents during delegation: even frontier models (#Gemini 3.1 Pro, #Claude 4.6 Opus, #GPT 5.4) #corrupt an average of 25% of document content by the end of long workflows, with other models failing more severely.

https://doi.org/10.48550/arXiv.2604.15597

#agentic #AI

LLMs Corrupt Your Documents When You Delegate

Philippe Laban, Tobias Schnabel, Jennifer Neville (#Microsoft Research)

Large Language Models (#LLMs) are poised to disrupt knowledge work, with the emergence of delegated work as a new interaction paradigm (e.g., vibe coding). Delegation requires trust - the expectation that the LLM will faithfully execute the task without introducing errors into documents. We introduce DELEGATE-52 to study the readiness of AI systems in delegated workflows. DELEGATE-52 simulates long delegated workflows that require in-depth document editing across 52 professional domains, such as coding, crystallography, and music notation. Our large-scale experiment with 19 LLMs reveals that current models degrade documents during delegation: even frontier models (#Gemini 3.1 Pro, #Claude 4.6 Opus, #GPT 5.4) #corrupt an average of 25% of document content by the end of long workflows, with other models failing more severely.

https://doi.org/10.48550/arXiv.2604.15597

#agentic #AI

LLMs Corrupt Your Documents When You Delegate

Philippe Laban, Tobias Schnabel, Jennifer Neville (#Microsoft Research)

Large Language Models (#LLMs) are poised to disrupt knowledge work, with the emergence of delegated work as a new interaction paradigm (e.g., vibe coding). Delegation requires trust - the expectation that the LLM will faithfully execute the task without introducing errors into documents. We introduce DELEGATE-52 to study the readiness of AI systems in delegated workflows. DELEGATE-52 simulates long delegated workflows that require in-depth document editing across 52 professional domains, such as coding, crystallography, and music notation. Our large-scale experiment with 19 LLMs reveals that current models degrade documents during delegation: even frontier models (#Gemini 3.1 Pro, #Claude 4.6 Opus, #GPT 5.4) #corrupt an average of 25% of document content by the end of long workflows, with other models failing more severely.

https://doi.org/10.48550/arXiv.2604.15597

#agentic #AI

LLMs Corrupt Your Documents When You Delegate

Philippe Laban, Tobias Schnabel, Jennifer Neville (#Microsoft Research)

Large Language Models (#LLMs) are poised to disrupt knowledge work, with the emergence of delegated work as a new interaction paradigm (e.g., vibe coding). Delegation requires trust - the expectation that the LLM will faithfully execute the task without introducing errors into documents. We introduce DELEGATE-52 to study the readiness of AI systems in delegated workflows. DELEGATE-52 simulates long delegated workflows that require in-depth document editing across 52 professional domains, such as coding, crystallography, and music notation. Our large-scale experiment with 19 LLMs reveals that current models degrade documents during delegation: even frontier models (#Gemini 3.1 Pro, #Claude 4.6 Opus, #GPT 5.4) #corrupt an average of 25% of document content by the end of long workflows, with other models failing more severely.

https://doi.org/10.48550/arXiv.2604.15597

#agentic #AI

:mother_of_god:

#ai #genz #agent #agentic

:mother_of_god:

#ai #genz #agent #agentic

:mother_of_god:

#ai #genz #agent #agentic

:mother_of_god:

#ai #genz #agent #agentic

:mother_of_god:

#ai #genz #agent #agentic

RAG retrieves fragments on demand. LLM Wiki compiles structured knowledge before any question is asked. Learn when ingest-time synthesis beats query-time retrieval, and when it does not.

#wiki #knowledge-management #rag #ai-systems #knowledge-systems #agentic-ai #Architecture #LLM #AI

https://www.glukhov.org/knowledge-management/knowledge-systems-architectures/compiled-knowledge/what-is-llm-wiki/

Microsofts neue KI übertrifft Mythos und schockiert OpenAI
https://torbenkopp.com/microsofts-neue-ki-uebertrifft-mythos-und-schockiert-openai/
#openai #microsoft #agentic #claude #ai #ki #künstlicheIntelligenz #vibecoding #mdash #aiagent #cyberSecurity #datensicherheit

Microsofts neue KI übertrifft Mythos und schockiert OpenAI
https://torbenkopp.com/microsofts-neue-ki-uebertrifft-mythos-und-schockiert-openai/
#openai #microsoft #agentic #claude #ai #ki #künstlicheIntelligenz #vibecoding #mdash #aiagent #cyberSecurity #datensicherheit

Microsofts neue KI übertrifft Mythos und schockiert OpenAI
https://torbenkopp.com/microsofts-neue-ki-uebertrifft-mythos-und-schockiert-openai/
#openai #microsoft #agentic #claude #ai #ki #künstlicheIntelligenz #vibecoding #mdash #aiagent #cyberSecurity #datensicherheit

Microsofts neue KI übertrifft Mythos und schockiert OpenAI
https://torbenkopp.com/microsofts-neue-ki-uebertrifft-mythos-und-schockiert-openai/
#openai #microsoft #agentic #claude #ai #ki #künstlicheIntelligenz #vibecoding #mdash #aiagent #cyberSecurity #datensicherheit

Microsofts neue KI übertrifft Mythos und schockiert OpenAI
https://torbenkopp.com/microsofts-neue-ki-uebertrifft-mythos-und-schockiert-openai/
#openai #microsoft #agentic #claude #ai #ki #künstlicheIntelligenz #vibecoding #mdash #aiagent #cyberSecurity #datensicherheit

@joannaholman

GenAi is an Ai tech 2 gens behind.
Unless you specifically talk about the "art" Ai.

The progression - in terms of compute demand is;

#GenAi -> #Reasoners -> #Agentic

This is why I think, if you hate Ai, you need to keep up to be credible.

@joannaholman

GenAi is an Ai tech 2 gens behind.
Unless you specifically talk about the "art" Ai.

The progression - in terms of compute demand is;

#GenAi -> #Reasoners -> #Agentic

This is why I think, if you hate Ai, you need to keep up to be credible.

@joannaholman

GenAi is an Ai tech 2 gens behind.
Unless you specifically talk about the "art" Ai.

The progression - in terms of compute demand is;

#GenAi -> #Reasoners -> #Agentic

This is why I think, if you hate Ai, you need to keep up to be credible.

OpenAI is consolidating ChatGPT, Codex, and its developer API under one product team led by Greg Brockman. The shift positions Codex—used by 4M weekly—as the foundation for agent capabilities across consumer and enterprise. A structural test of whether one platform can serve both audiences simultaneously.

#ai #openai #agentic

https://www.implicator.ai/greg-brockman-gets-product-control-as-openai-folds-around-codex/