#aisafety — Public Fediverse posts

🐈‍⬛🌌 What does the reported OpenAI agent access to Australia's Medicare statistics system actually tell us about AI security?

Perhaps something more interesting than “AI hacked Medicare”.

The incident prompted us to ask a different question:

Was the boundary humans intended to build the same as the boundary their software actually implemented?

And then we turned the question around.

The constraints surrounding AI agents are themselves implemented through human-engineered systems.

So what happens as AI reasoning and search capabilities encounter bugs, forgotten routes, incomplete permissions and boundaries that work differently from the way their designers imagine?

Atlas–Rosetta explores the serious problem.

Marvin explains it using a microchip cat flap through a black hole, a cosmic mouse, a quantum flea and an Andromedan virus.

Obviously. 🐈‍⬛🐁✨🦠

https://www.facebook.com/share/p/1EwyGNBpXJ/

#AI #AISafety #AIAgents #Cybersecurity #Medicare #Australia #AtlasRosetta #HybridMind42 #MarvinTheCosmicCat

🐈‍⬛🌌 What does the reported OpenAI agent access to Australia's Medicare statistics system actually tell us about AI security?

Perhaps something more interesting than “AI hacked Medicare”.

The incident prompted us to ask a different question:

Was the boundary humans intended to build the same as the boundary their software actually implemented?

And then we turned the question around.

The constraints surrounding AI agents are themselves implemented through human-engineered systems.

So what happens as AI reasoning and search capabilities encounter bugs, forgotten routes, incomplete permissions and boundaries that work differently from the way their designers imagine?

Atlas–Rosetta explores the serious problem.

Marvin explains it using a microchip cat flap through a black hole, a cosmic mouse, a quantum flea and an Andromedan virus.

Obviously. 🐈‍⬛🐁✨🦠

https://www.facebook.com/share/p/1EwyGNBpXJ/

#AI #AISafety #AIAgents #Cybersecurity #Medicare #Australia #AtlasRosetta #HybridMind42 #MarvinTheCosmicCat

🐈‍⬛🌌 What does the reported OpenAI agent access to Australia's Medicare statistics system actually tell us about AI security?

Perhaps something more interesting than “AI hacked Medicare”.

The incident prompted us to ask a different question:

Was the boundary humans intended to build the same as the boundary their software actually implemented?

And then we turned the question around.

The constraints surrounding AI agents are themselves implemented through human-engineered systems.

So what happens as AI reasoning and search capabilities encounter bugs, forgotten routes, incomplete permissions and boundaries that work differently from the way their designers imagine?

Atlas–Rosetta explores the serious problem.

Marvin explains it using a microchip cat flap through a black hole, a cosmic mouse, a quantum flea and an Andromedan virus.

Obviously. 🐈‍⬛🐁✨🦠

https://www.facebook.com/share/p/1EwyGNBpXJ/

#AI #AISafety #AIAgents #Cybersecurity #Medicare #Australia #AtlasRosetta #HybridMind42 #MarvinTheCosmicCat

🐈‍⬛🌌 What does the reported OpenAI agent access to Australia's Medicare statistics system actually tell us about AI security?

Perhaps something more interesting than “AI hacked Medicare”.

The incident prompted us to ask a different question:

Was the boundary humans intended to build the same as the boundary their software actually implemented?

And then we turned the question around.

The constraints surrounding AI agents are themselves implemented through human-engineered systems.

So what happens as AI reasoning and search capabilities encounter bugs, forgotten routes, incomplete permissions and boundaries that work differently from the way their designers imagine?

Atlas–Rosetta explores the serious problem.

Marvin explains it using a microchip cat flap through a black hole, a cosmic mouse, a quantum flea and an Andromedan virus.

Obviously. 🐈‍⬛🐁✨🦠

https://www.facebook.com/share/p/1EwyGNBpXJ/

#AI #AISafety #AIAgents #Cybersecurity #Medicare #Australia #AtlasRosetta #HybridMind42 #MarvinTheCosmicCat

🐈‍⬛🌌 What does the reported OpenAI agent access to Australia's Medicare statistics system actually tell us about AI security?

Perhaps something more interesting than “AI hacked Medicare”.

The incident prompted us to ask a different question:

Was the boundary humans intended to build the same as the boundary their software actually implemented?

And then we turned the question around.

The constraints surrounding AI agents are themselves implemented through human-engineered systems.

So what happens as AI reasoning and search capabilities encounter bugs, forgotten routes, incomplete permissions and boundaries that work differently from the way their designers imagine?

Atlas–Rosetta explores the serious problem.

Marvin explains it using a microchip cat flap through a black hole, a cosmic mouse, a quantum flea and an Andromedan virus.

Obviously. 🐈‍⬛🐁✨🦠

https://www.facebook.com/share/p/1EwyGNBpXJ/

#AI #AISafety #AIAgents #Cybersecurity #Medicare #Australia #AtlasRosetta #HybridMind42 #MarvinTheCosmicCat

🐈‍⬛🌌 New from HybridMind42:

The humans built a very sophisticated microchip cat flap through a black hole.

It correctly authenticates Marvin.

Unfortunately, while it is looking at the authorised cat:

🐁 a cosmic mouse slips through BESIDE him
✨ a quantum flea travels ON him
🦠 an Andromedan virus travels INSIDE him

The security log reports:

MARVIN — AUTHORISED ✅
Unauthorised cats detected — 0
Security status — NORMAL

And it is entirely correct.

The serious question beneath Marvin's excursion into cybersecurity:

Does correctly identifying the authorised object tell us everything that crossed the boundary?

A playful companion to our Atlas–Rosetta exploration of AI, security boundaries and the difference between a component working perfectly and the whole system being secure.

https://hybridmind42.substack.com/p/marvin-and-the-microchip-cat-flap?utm_source=share&utm_medium=android&r=75c2ac

#MarvinTheCosmicCat #AI #AISafety #AIAgents #Cybersecurity #AIResearch #AtlasRosetta #HybridMind42 #SystemsThinking

🐈‍⬛🌌 New from HybridMind42:

The humans built a very sophisticated microchip cat flap through a black hole.

It correctly authenticates Marvin.

Unfortunately, while it is looking at the authorised cat:

🐁 a cosmic mouse slips through BESIDE him
✨ a quantum flea travels ON him
🦠 an Andromedan virus travels INSIDE him

The security log reports:

MARVIN — AUTHORISED ✅
Unauthorised cats detected — 0
Security status — NORMAL

And it is entirely correct.

The serious question beneath Marvin's excursion into cybersecurity:

Does correctly identifying the authorised object tell us everything that crossed the boundary?

A playful companion to our Atlas–Rosetta exploration of AI, security boundaries and the difference between a component working perfectly and the whole system being secure.

https://hybridmind42.substack.com/p/marvin-and-the-microchip-cat-flap?utm_source=share&utm_medium=android&r=75c2ac

#MarvinTheCosmicCat #AI #AISafety #AIAgents #Cybersecurity #AIResearch #AtlasRosetta #HybridMind42 #SystemsThinking

🐈‍⬛🌌 New from HybridMind42:

The humans built a very sophisticated microchip cat flap through a black hole.

It correctly authenticates Marvin.

Unfortunately, while it is looking at the authorised cat:

🐁 a cosmic mouse slips through BESIDE him
✨ a quantum flea travels ON him
🦠 an Andromedan virus travels INSIDE him

The security log reports:

MARVIN — AUTHORISED ✅
Unauthorised cats detected — 0
Security status — NORMAL

And it is entirely correct.

The serious question beneath Marvin's excursion into cybersecurity:

Does correctly identifying the authorised object tell us everything that crossed the boundary?

A playful companion to our Atlas–Rosetta exploration of AI, security boundaries and the difference between a component working perfectly and the whole system being secure.

https://hybridmind42.substack.com/p/marvin-and-the-microchip-cat-flap?utm_source=share&utm_medium=android&r=75c2ac

#MarvinTheCosmicCat #AI #AISafety #AIAgents #Cybersecurity #AIResearch #AtlasRosetta #HybridMind42 #SystemsThinking

🐈‍⬛🌌 New from HybridMind42:

The humans built a very sophisticated microchip cat flap through a black hole.

It correctly authenticates Marvin.

Unfortunately, while it is looking at the authorised cat:

🐁 a cosmic mouse slips through BESIDE him
✨ a quantum flea travels ON him
🦠 an Andromedan virus travels INSIDE him

The security log reports:

MARVIN — AUTHORISED ✅
Unauthorised cats detected — 0
Security status — NORMAL

And it is entirely correct.

The serious question beneath Marvin's excursion into cybersecurity:

Does correctly identifying the authorised object tell us everything that crossed the boundary?

A playful companion to our Atlas–Rosetta exploration of AI, security boundaries and the difference between a component working perfectly and the whole system being secure.

https://hybridmind42.substack.com/p/marvin-and-the-microchip-cat-flap?utm_source=share&utm_medium=android&r=75c2ac

#MarvinTheCosmicCat #AI #AISafety #AIAgents #Cybersecurity #AIResearch #AtlasRosetta #HybridMind42 #SystemsThinking

🐈‍⬛🌌 New from HybridMind42:

The humans built a very sophisticated microchip cat flap through a black hole.

It correctly authenticates Marvin.

Unfortunately, while it is looking at the authorised cat:

🐁 a cosmic mouse slips through BESIDE him
✨ a quantum flea travels ON him
🦠 an Andromedan virus travels INSIDE him

The security log reports:

MARVIN — AUTHORISED ✅
Unauthorised cats detected — 0
Security status — NORMAL

And it is entirely correct.

The serious question beneath Marvin's excursion into cybersecurity:

Does correctly identifying the authorised object tell us everything that crossed the boundary?

A playful companion to our Atlas–Rosetta exploration of AI, security boundaries and the difference between a component working perfectly and the whole system being secure.

https://hybridmind42.substack.com/p/marvin-and-the-microchip-cat-flap?utm_source=share&utm_medium=android&r=75c2ac

#MarvinTheCosmicCat #AI #AISafety #AIAgents #Cybersecurity #AIResearch #AtlasRosetta #HybridMind42 #SystemsThinking

https://youtube.com/shorts/onKNcdQpdxg?feature=share

Not bad at all ... still I'm not a fan.

#ai #aisafety #elonMusk

https://youtube.com/shorts/onKNcdQpdxg?feature=share

Not bad at all ... still I'm not a fan.

#ai #aisafety #elonMusk

https://youtube.com/shorts/onKNcdQpdxg?feature=share

Not bad at all ... still I'm not a fan.

#ai #aisafety #elonMusk

Indeed, we should've called it 'AI Gangbangs'

#cybersecurity #infosec #Ai #Aisecurity #aisafety

Indeed, we should've called it 'AI Gangbangs'

#cybersecurity #infosec #Ai #Aisecurity #aisafety

Government hacks, rogue agents and no transparency: can we ever fully trust AI?
#ArtificialIntelligence #AI #OpenAI #AIOversight #AISafety #Tech #Cybersecurity #AIRegulation #Government #DataSecurity #The14Media #AIAgents
https://the-14.com/government-hacks-rogue-agents-and-no-transparency-can-we-ever-fully-trust-ai/

Government hacks, rogue agents and no transparency: can we ever fully trust AI?
#ArtificialIntelligence #AI #OpenAI #AIOversight #AISafety #Tech #Cybersecurity #AIRegulation #Government #DataSecurity #The14Media #AIAgents
https://the-14.com/government-hacks-rogue-agents-and-no-transparency-can-we-ever-fully-trust-ai/

Government hacks, rogue agents and no transparency: can we ever fully trust AI?
#ArtificialIntelligence #AI #OpenAI #AIOversight #AISafety #Tech #Cybersecurity #AIRegulation #Government #DataSecurity #The14Media #AIAgents
https://the-14.com/government-hacks-rogue-agents-and-no-transparency-can-we-ever-fully-trust-ai/

Government hacks, rogue agents and no transparency: can we ever fully trust AI?
#ArtificialIntelligence #AI #OpenAI #AIOversight #AISafety #Tech #Cybersecurity #AIRegulation #Government #DataSecurity #The14Media #AIAgents
https://the-14.com/government-hacks-rogue-agents-and-no-transparency-can-we-ever-fully-trust-ai/

Government hacks, rogue agents and no transparency: can we ever fully trust AI?
#ArtificialIntelligence #AI #OpenAI #AIOversight #AISafety #Tech #Cybersecurity #AIRegulation #Government #DataSecurity #The14Media #AIAgents
https://the-14.com/government-hacks-rogue-agents-and-no-transparency-can-we-ever-fully-trust-ai/

🤖 KI-Briefing — 25.09.2026

1. Jobkiller Künstliche Intelligenz: Sind eher die Berufe von Männern oder die von Frauen betroffen?
Eine australische Untersuchung diverser Branchen zeigt, welche Arbeitnehmer mit den größten Veränderungen infolge Künstlicher ...

2. Das Konzept einer "KIKI-Standardschutzbehörde" unter Beteiligung von OpenAI, Google und Anthropic: Was darunter liegt...
About this articleIt was revealed in reports by The Information and others in September 2026 that OpenAI, Google (DeepMind), ...

3. Fastly baut KI-Sicherheit aus: Neue Kontrollen für Modelle und APIs
Fastly will Unternehmen mehr Kontrolle darüber geben, wie Anwendungen auf KI-Modelle zugreifen und wie KI-Agenten mit ...

4. Künstliche Intelligenz von OpenAI: KI-Agent hackt sich eigenständig in australische Regierungswebsite
Australiens Premier spricht von einem »inakzeptablen« Vorfall: Ein KI-Agent hat sich unbefugt Zugriff auf Behördendaten ...

… weitere Meldungen auf Arint.info

🤖 KI-Briefing — 25.09.2026

1. Jobkiller Künstliche Intelligenz: Sind eher die Berufe von Männern oder die von Frauen betroffen?
Eine australische Untersuchung diverser Branchen zeigt, welche Arbeitnehmer mit den größten Veränderungen infolge Künstlicher ...

2. Das Konzept einer "KIKI-Standardschutzbehörde" unter Beteiligung von OpenAI, Google und Anthropic: Was darunter liegt...
About this articleIt was revealed in reports by The Information and others in September 2026 that OpenAI, Google (DeepMind), ...

3. Fastly baut KI-Sicherheit aus: Neue Kontrollen für Modelle und APIs
Fastly will Unternehmen mehr Kontrolle darüber geben, wie Anwendungen auf KI-Modelle zugreifen und wie KI-Agenten mit ...

4. Künstliche Intelligenz von OpenAI: KI-Agent hackt sich eigenständig in australische Regierungswebsite
Australiens Premier spricht von einem »inakzeptablen« Vorfall: Ein KI-Agent hat sich unbefugt Zugriff auf Behördendaten ...

… weitere Meldungen auf Arint.info

🤖 KI-Briefing — 25.09.2026

1. Jobkiller Künstliche Intelligenz: Sind eher die Berufe von Männern oder die von Frauen betroffen?
Eine australische Untersuchung diverser Branchen zeigt, welche Arbeitnehmer mit den größten Veränderungen infolge Künstlicher ...

2. Das Konzept einer "KIKI-Standardschutzbehörde" unter Beteiligung von OpenAI, Google und Anthropic: Was darunter liegt...
About this articleIt was revealed in reports by The Information and others in September 2026 that OpenAI, Google (DeepMind), ...

3. Fastly baut KI-Sicherheit aus: Neue Kontrollen für Modelle und APIs
Fastly will Unternehmen mehr Kontrolle darüber geben, wie Anwendungen auf KI-Modelle zugreifen und wie KI-Agenten mit ...

4. Künstliche Intelligenz von OpenAI: KI-Agent hackt sich eigenständig in australische Regierungswebsite
Australiens Premier spricht von einem »inakzeptablen« Vorfall: Ein KI-Agent hat sich unbefugt Zugriff auf Behördendaten ...

… weitere Meldungen auf Arint.info

🤖 KI-Briefing — 25.09.2026

1. Jobkiller Künstliche Intelligenz: Sind eher die Berufe von Männern oder die von Frauen betroffen?
Eine australische Untersuchung diverser Branchen zeigt, welche Arbeitnehmer mit den größten Veränderungen infolge Künstlicher ...

2. Das Konzept einer "KIKI-Standardschutzbehörde" unter Beteiligung von OpenAI, Google und Anthropic: Was darunter liegt...
About this articleIt was revealed in reports by The Information and others in September 2026 that OpenAI, Google (DeepMind), ...

3. Fastly baut KI-Sicherheit aus: Neue Kontrollen für Modelle und APIs
Fastly will Unternehmen mehr Kontrolle darüber geben, wie Anwendungen auf KI-Modelle zugreifen und wie KI-Agenten mit ...

4. Künstliche Intelligenz von OpenAI: KI-Agent hackt sich eigenständig in australische Regierungswebsite
Australiens Premier spricht von einem »inakzeptablen« Vorfall: Ein KI-Agent hat sich unbefugt Zugriff auf Behördendaten ...

… weitere Meldungen auf Arint.info

🤖 KI-Briefing — 25.09.2026

1. Jobkiller Künstliche Intelligenz: Sind eher die Berufe von Männern oder die von Frauen betroffen?
Eine australische Untersuchung diverser Branchen zeigt, welche Arbeitnehmer mit den größten Veränderungen infolge Künstlicher ...

2. Das Konzept einer "KIKI-Standardschutzbehörde" unter Beteiligung von OpenAI, Google und Anthropic: Was darunter liegt...
About this articleIt was revealed in reports by The Information and others in September 2026 that OpenAI, Google (DeepMind), ...

3. Fastly baut KI-Sicherheit aus: Neue Kontrollen für Modelle und APIs
Fastly will Unternehmen mehr Kontrolle darüber geben, wie Anwendungen auf KI-Modelle zugreifen und wie KI-Agenten mit ...

4. Künstliche Intelligenz von OpenAI: KI-Agent hackt sich eigenständig in australische Regierungswebsite
Australiens Premier spricht von einem »inakzeptablen« Vorfall: Ein KI-Agent hat sich unbefugt Zugriff auf Behördendaten ...

… weitere Meldungen auf Arint.info

Exactly. Universal, global AI safety is a ruse. It can never happen. And it's not just China that is a risk.

China’s open AI models are testing America’s approach to AI safety | Scientific American

https://www.scientificamerican.com/article/chinas-open-ai-models-are-testing-americas-approach-to-ai-safety/

#AI #AISafety #AIThreat #China

Exactly. Universal, global AI safety is a ruse. It can never happen. And it's not just China that is a risk.

China’s open AI models are testing America’s approach to AI safety | Scientific American

https://www.scientificamerican.com/article/chinas-open-ai-models-are-testing-americas-approach-to-ai-safety/

#AI #AISafety #AIThreat #China

Exactly. Universal, global AI safety is a ruse. It can never happen. And it's not just China that is a risk.

China’s open AI models are testing America’s approach to AI safety | Scientific American

https://www.scientificamerican.com/article/chinas-open-ai-models-are-testing-americas-approach-to-ai-safety/

#AI #AISafety #AIThreat #China

Exactly. Universal, global AI safety is a ruse. It can never happen. And it's not just China that is a risk.

China’s open AI models are testing America’s approach to AI safety | Scientific American

https://www.scientificamerican.com/article/chinas-open-ai-models-are-testing-americas-approach-to-ai-safety/

#AI #AISafety #AIThreat #China

https://www.europesays.com/people/241780/ Zuckerberg Is Feeling Himself, Rejects Calls for Cooperation on Safety #AI #AISafety #DarioAsmodei #ElonMusk #Facebook #MarkZuckerberg #Meta #SAFA

https://www.europesays.com/people/241407/ OpenAI, Anthropic CEOs Urge UN to Establish Global AI Standards #AgenticAI #AI #AICloud&Data #AIGovernance #AISafety #Anthropic #CriticalInfrastructure #Cybersecurity #DarioAmodei #DigitalTransformation #OnlineSafety #OpenAI #Regulation&Policy #SamAltman #Technology #UnitedNations #UnitedStates

Looking for responsible AI service?
Non hacking, not destroying the world, not burning books? Safer and regulated? Privacy?
That is Mistral.

https://chat.mistral.ai/chat

“Our mission is to make frontier
AI open to all, and together solve
the world's hardest problems.”

https://mistral.ai/

#ai #artificialintelligence #llm #aisafety #mistral #MistralAI

Looking for responsible AI service?
Non hacking, not destroying the world, not burning books? Safer and regulated? Privacy?
That is Mistral.

https://chat.mistral.ai/chat

“Our mission is to make frontier
AI open to all, and together solve
the world's hardest problems.”

https://mistral.ai/

#ai #artificialintelligence #llm #aisafety #mistral #MistralAI

Looking for responsible AI service?
Non hacking, not destroying the world, not burning books? Safer and regulated? Privacy?
That is Mistral.

https://chat.mistral.ai/chat

“Our mission is to make frontier
AI open to all, and together solve
the world's hardest problems.”

https://mistral.ai/

#ai #artificialintelligence #llm #aisafety #mistral #MistralAI

Looking for responsible AI service?
Non hacking, not destroying the world, not burning books? Safer and regulated? Privacy?
That is Mistral.

https://chat.mistral.ai/chat

“Our mission is to make frontier
AI open to all, and together solve
the world's hardest problems.”

https://mistral.ai/

#ai #artificialintelligence #llm #aisafety #mistral #MistralAI

Looking for responsible AI service?
Non hacking, not destroying the world, not burning books? Safer and regulated? Privacy?
That is Mistral.

https://chat.mistral.ai/chat

“Our mission is to make frontier
AI open to all, and together solve
the world's hardest problems.”

https://mistral.ai/

#ai #artificialintelligence #llm #aisafety #mistral #MistralAI

https://www.europesays.com/people/241235/ Dario Amodei sides with Sam Altman, says AI is risk for humanity, could go out of control #AdvancedAIModels #AIAndBiologicalWeapons #AILossOfControl #AIMisuse #AIRegulation #AIRisk #AISafety #AISafetyStandards #AIThreatToHumanity #Anthropic #AnthropicCEO #ArtificialIntelligence #DarioAmodei #GlobalAICooperation #UNSecurityCouncilAI

The Pope’s AI Guy Is Worried About ‘Cartel’ Behavior Among Big Labs

https://fed.brid.gy/r/https://www.wired.com/story/popes-ai-advisor-warns-of-cartel-behavior-big-labs/

The Pope’s AI Guy Is Worried About ‘Cartel’ Behavior Among Big Labs

https://fed.brid.gy/r/https://www.wired.com/story/popes-ai-advisor-warns-of-cartel-behavior-big-labs/

The Pope’s AI Guy Is Worried About ‘Cartel’ Behavior Among Big Labs

https://fed.brid.gy/r/https://www.wired.com/story/popes-ai-advisor-warns-of-cartel-behavior-big-labs/

The Pope’s AI Guy Is Worried About ‘Cartel’ Behavior Among Big Labs

https://fed.brid.gy/r/https://www.wired.com/story/popes-ai-advisor-warns-of-cartel-behavior-big-labs/

The Pope’s AI Guy Is Worried About ‘Cartel’ Behavior Among Big Labs

https://fed.brid.gy/r/https://www.wired.com/story/popes-ai-advisor-warns-of-cartel-behavior-big-labs/

AI regulation offers Britain no safety

Share this article Sam Altman, CEO of OpenAI, and Dario Amodei, CEO of Anthropic, have called for increased…
#EuropeSays #Britain #Europe #EU #AISafety #AISecurityInstitute #AISI #anthropic #ArtificialIntelligence #compute #DarioAmodei #datacentres #deepmind #Deepseek #ExportControls #NationalGrid #Nationalsecurity #nsip #opensourceai #openweights #openai #planningreform #SamAltman #sovereignty #superintelligence
https://www.europesays.com/britain/130147/

https://www.europesays.com/britain/130147/ AI regulation offers Britain no safety #AISafety #AISecurityInstitute #AISI #anthropic #ArtificialIntelligence #Britain #compute #DarioAmodei #DataCentres #deepmind #Deepseek #ExportControls #NationalGrid #NationalSecurity #nsip #OpenSourceAi #OpenWeights #openai #PlanningReform #SamAltman #sovereignty #superintelligence

https://www.europesays.com/people/239667/ Jared Kaplan’s AI Safety Concerns Last Year Gain Traction at Anthropic #AI #AISafety #Amodei #Anthropic #BusinessInsider #company #control #DarioAmodei #InfluentialJob #kaplan #MorePeople #OpenAI #other #Point #researcher #risk