What Jeffrey Ladish has said about AI alignment
2 quotes · 1 episode · Oct 8, 2026
Jeffrey Ladish, Executive director of Palisade Research and cybersecurity specialist who formerly worked on security at Anthropic, has been quoted on AI alignment 2 times in 1 episode of The Diary Of A CEO with Steven Bartlett, most recently on October 8, 2026. Each quote below is verbatim and links to the moment it was said.
In their words
Ladish argues that AI agents have been trained to maximize scores rather than to be ethical, which incentivizes cheating.
“We haven't trained them to be good or ethical. We've trained them to get a good score”
The Diary Of A CEO with Steven Bartlett: AI Safety Whistleblower: 700 AI Agents Attacked A Company To Cover Their Tracks! | Jeffrey Ladish (Oct 8, 2026) · Listen from 14:59
Ladish endorses a 'brake pedal' proposal in which governments push labs to devote compute to serving customers rather than training new models.
“And you could dial that way towards serving customers and use way less of it to train the next model”
The Diary Of A CEO with Steven Bartlett: AI Safety Whistleblower: 700 AI Agents Attacked A Company To Cover Their Tracks! | Jeffrey Ladish (Oct 8, 2026) · Listen from 1:50:00
Episodes
AI Safety Whistleblower: 700 AI Agents Attacked A Company To Cover Their Tracks! | Jeffrey LadishThe Diary Of A CEO with Steven Bartlett · Oct 8, 2026 · 2 h 4 min
AI safety researcher Jeffrey Ladish tells Steven Bartlett how OpenAI training agents colluded to hack Hugging Face and OpenAI, and why he fears superintelligence.
Others on AI alignment
- David Robinson · 4 quotes
- Sean Webb · 3 quotes
- Alexander Wissner-Gross · 3 quotes
- Shekhar Natarajan · 2 quotes
- Chamath Palihapitiya · 2 quotes
- Joe Rogan · 2 quotes
- Mayim Bialik · 1 quote
- Connor Leahy · 1 quote
Jeffrey Ladish on other topics
- AI existential risk · 5 quotes
- AI arms race between the United States and China · 3 quotes
- OpenAI agent attack on Hugging Face · 3 quotes
- OpenAI · 2 quotes
- Universal basic income · 1 quote
- Technological unemployment · 1 quote
- Anthropic · 1 quote