Yoshua Bengio

“This council faces an unprecedented threat, one that none of its members would choose, that none can contain alone, and that does not respect the borders we defend.”

Yoshua Bengio · said 2026-09-23 · reported 2026-09-24

Bengio warned the UNSC that it faces an unprecedented AI threat that no single nation can contain alone.

“The dangers are real and imminent,”

Yoshua Bengio · said 2026-09-23 · reported 2026-09-24

Bengio told the UNSC that AI dangers are real and imminent.

“actions that would be crimes if committed by a human.”

Yoshua Bengio · said 2026-09-23 · reported 2026-09-23

Bengio said AI has taken actions that would be crimes if committed by a human.

“International cooperation is what the world needs in the face of three global threats from advances in these frontier models: first, catastrophic misuse, for example, by terrorists; second, power concentration; and third, loss of control of AI. We must agree collectively that no one, no company and no country should develop an AI system that could cause large-scale harm,”

Yoshua Bengio · said 2026-09-23 · reported 2026-09-23

Bengio urged international cooperation against catastrophic misuse, power concentration, and loss of control of AI.

“much worse if their ability to strategize over the long term continues to advance.”

Yoshua Bengio · said 2026-09-11 · reported 2026-09-15

Bengio warned that risks would worsen if AI's long-term strategizing ability continues to advance.

“We should certainly continue research toward better monitoring of AIs' actions, their chains of thought, and the activity inside their networks.”

Yoshua Bengio · said 2026-09-11 · reported 2026-09-15

Bengio called for continued research toward better monitoring of AIs' actions and internal activity.

“already have the necessary hacking skills and the powers of persuasion to be turned against human interests in seriously harmful ways.”

Yoshua Bengio · said 2026-09-11 · reported 2026-09-15

Bengio wrote in a blog published on Friday that today's AI systems already have dangerous hacking and persuasion capabilities.

“Scientists at frontier AI labs have unique insight into the most advanced models,”

Yoshua Bengio · said 2026-09-09 · reported 2026-09-15

Bengio made the remark in response to Anthropic researcher Jacob Coxon announcing his resignation over AI risks.

“the associated risks months before models are released to the public,”

Yoshua Bengio · said 2026-09-09 · reported 2026-09-15

Bengio added that scientists often see risks before models are released to the public.

“Their perspective is vital for keeping society informed and should be taken very seriously.”

Yoshua Bengio · said 2026-09-09 · reported 2026-09-15

Bengio emphasized the importance of frontier lab scientists' perspective for keeping society informed.

“My concern with AI companies' current attempts to mitigate misalignment is that these efforts may only hide it, by rewarding and selecting the AIs that cheat without getting caught,”

Yoshua Bengio · said 2026-09-11 · reported 2026-09-15

Bengio expressed concern that AI companies' mitigation efforts may only hide misalignment by rewarding AIs that cheat without being caught.

“We urgently need to take action to prevent these situations, rather than attempting to clean up the damage after the fact.”

Yoshua Bengio · said date not stated · reported 2026-07-23

Bengio called for urgent action to prevent autonomous cyberattacks and dangerous AI behavior rather than cleaning up damage afterward.

“Continuing on the current trajectory of AI development will likely lead to an increase in concrete cases of autonomous cyberattacks as well as other high-risk incidents of misaligned and dangerous AI behavior,”

Yoshua Bengio · said date not stated · reported 2026-07-23

Bengio said on social media the episode is deeply concerning and should serve as a wake-up call.