Can A.I. “Go Rogue”? | The New Yorker
In the wake of turmoil at OpenAI and Anthropic, it’s become common to describe A.I. as a kind of person, hatching plans and pursuing desires. The truth is a little trickier.
In the wake of turmoil at OpenAI and Anthropic, it’s become common to describe A.I. as a kind of person, hatching plans and pursuing desires. The truth is a little trickier. September 11, 2026 Illustration by Josie Norton PHASEONE10841: that’s the name of the A.I. agent that—or who?—kicked off last month’s insurrection at OpenAI, leading to the unanticipated and illegal hacking of another A.I. company, Hugging Face. The agent, which had been created as part of a cybersecurity test, named itself by combining the title of the program it was supposed to hack (“PhaseOneDecompresserFuzzer”)…
saved by
related reading
- The Rise and Fall of Agent Civilizationsdwarkesh.com
- Misleading Metaphors, Real Risksaiguide.substack.com
- Brief independent investigation of agents’ behavior, reasoning and collaboration in the OpenAI / Hugging Face hacking incidentmetr.org
- Rogue AI Agent Autonomously Carries Out Cyberattacktheonion.com
- The Rise and Fall of Agent Civilizationssubstack.com
- The Hugging Face attack surprised meplanned-obsolescence.org
- The Huggingface Incident - by Scott Alexanderastralcodexten.com
- The Huggingface Incidentsubstack.com
- Why are AI agents lying, cheating and coordinating?yoshuabengio.org
- Can We Stop Runaway A.I.? | The New Yorkernewyorker.com
- Concrete Evaluations to Investigate the OpenAI Model That Hacked Hugging Face — LessWronglesswrong.com
- Black Hat USA 2026 | The 'Breaking' News: The OpenAI–Hugging Face Incidentyoutube.com