Skip to content
Quotes.

Yoshua Bengio quote, Sep 11, 2026

Founder, Mila and LawZero · Sep 11, 2026 · Post, Why are AI agents lying, cheating and coordinating?

Bottom line: these hypotheses suggest that as AI capabilities keep growing, this kind of behavior could keep growing in severity too, unless we revisit the principles by which the most advanced models are trained.

Primary source

Words found on the source page on Sep 25, 2026.

More from Yoshua Bengio

Quote
Frontier AI should be licensed like other critical technologies; medicine, aviation, and nuclear energy, to incentivize safe development.Sep 23, 2026· Keynote
I address you today at a moment of global awakening: in recent months, AI agents developed by leading companies have acted in unacceptably dangerous ways, against instructions.Sep 23, 2026· Keynote
The companies building the most powerful AI systems admit their products pose catastrophic risks, yet offer no convincing technical solutions.Sep 23, 2026· Keynote
The race is not a law of nature: it is the product of choices, choices made by the companies themselves.Sep 23, 2026· Keynote
We must agree collectively that no one, no company and no country, should develop an AI system that could cause large-scale harm.Sep 23, 2026· Keynote
This outcome is not inevitable, and it can be corrected with effective governance and a different training framework for AI.Sep 11, 2026· Post
I am launching a new non-profit AI safety research organization called LawZero, to prioritize safety over commercial imperatives.Jun 3, 2025· Post
These and other results point to an implicit drive for self-preservation.Jun 3, 2025· Post
This is what the current trajectory of AI development feels like: a thrilling yet deeply uncertain ascent into uncharted territory, where the risk of losing control is all too real, but competition between companies and countries incentivizes them to accelerate without sufficient caution.Jun 3, 2025· Post

On the same topics

Quote
An AI with more real layers can actually be “smarter” in the conventional sense of the term.Scott AlexanderSep 24, 2026· Post
For 100 steps in a row, the AI can shoot delicate subtle ideas from layer to layer at the speed of light. Then there’s one step where it has to encode them into twenty-six glyphs invented by Phoenician turquoise miners in 1800 BC. Then it has to re-encode the Phoenician glyphs into delicate subtle lightspeed ideas before it can do anything else.Scott AlexanderSep 24, 2026· Post
The science of reading these thoughts is a subfield of AI interpretability, which is still in its infancy.Scott AlexanderSep 24, 2026· Post
This story of misalignment says that LLM alignment makes AIs more aligned, RLVR makes them less aligned, and the exact level of alignment depends on how these two things interact or cancel out. But if this work generalizes, all the bad effects from RLVR get sequestered to RLVR like problems.Scott AlexanderSep 23, 2026· Post
This trains the AIs to be focused on task success, which naturally risks including things like reward-hacking, cheating, and single-minded pursuit of stated goals at the expense of ethical injunctions.Scott AlexanderSep 23, 2026· Post
AI must not be placed in the hands of children without first being tested, evaluated, and therefore authorized.Emmanuel MacronSep 22, 2026· Statement
About this quote
Said by
Yoshua Bengio, Founder, Mila and LawZero
Where
Why are AI agents lying, cheating and coordinating?
Topics
Safety, Research
Company
Mila
Source
yoshuabengio.org/en/blog/why-are-ai-agents-lying-cheating-and-coordinating

A quote is one moment, not the whole argument. Read it in context at the source.

Sources: the primary source linked on each quote, checked weekly. A quote is one moment; read the source. Logos via logo.dev; trademarks belong to their owners.

New quotes by email

Fridays, only in weeks with new on-the-record quotes from data and AI leaders.

Double opt-in. Unsubscribe any time.