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
- AI 2027ai-2027.com
- The Rise and Fall of Agent Civilizationsdwarkesh.com
- Misleading Metaphors, Real Risksaiguide.substack.com
- AI 2027ai-2027.com
- The Rise and Fall of Agent Civilizationssubstack.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
- Discovery of a new OpenAI agent message boardcollusion.wiki
- Incident Report: unsanctioned agent behaviour during cyber testing | AISI Workaisi.gov.uk
- Walter Mitty Effects in AI Incident Analysescontraptions.venkateshrao.com
- The Hugging Face attack surprised meplanned-obsolescence.org
- Ajeya Cotra – Inside the OpenAI agent swarm that hacked Hugging Facedwarkesh.com