Quotesby GlyphYoshua Bengio quote, Jun 3, 2025
Founder, Mila and LawZero · Jun 3, 2025 1 year ago · Blog, Introducing LawZero
These and other results point to an implicit drive for self-preservation.
Words found on the source page on Nov 6, 2026.
More from Yoshua Bengio
- Frontier AI should be licensed like other critical technologies; medicine, aviation, and nuclear energy, to incentivize safe development.
- 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.
- The companies building the most powerful AI systems admit their products pose catastrophic risks, yet offer no convincing technical solutions.
- The race is not a law of nature: it is the product of choices, choices made by the companies themselves.
- We must agree collectively that no one, no company and no country, should develop an AI system that could cause large-scale harm.
- 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.
- This outcome is not inevitable, and it can be corrected with effective governance and a different training framework for AI.
- I am launching a new non-profit AI safety research organization called LawZero, to prioritize safety over commercial imperatives.
- 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.
On the same topics
- The science of reading these thoughts is a subfield of AI interpretability, which is still in its infancy.
- 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.
- 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.
- AI must not be placed in the hands of children without first being tested, evaluated, and therefore authorized.
- We cannot repeat the mistakes of the past and wait twenty years to see the impact of chatbots on minors.
- Indeed, that’s probably the overhang that matters most of all: competition. Anthropic is fine with Anthropic being in the lead; anyone else requires government intervention.
About this quote
- Said by
- Yoshua Bengio, Founder, Mila and LawZero
- Where
- Introducing LawZero
- Topics
- Safety
- Company
Mila
- Source
- yoshuabengio.org/en/blog/introducing-lawzero
A quote is one moment, not the whole argument. Read it in context at the source.