Cyberattack AIs must be trained only on air-gapped systems, hundreds of AI researchers say
487 AI researchers, including Hinton and Bengio, urge air-gapping cyber-capable models and a new international safety body.
Stories per day · 30 days
1 RSS
Relatedai-safety2containment2geoffrey-hinton2open-letter2air-gapping1airgapping1alignment1cyber-capable-ai1
6 stories, newest first · one card per story
Stories tagged #yoshua-bengio
406 scientists demand AI models be cut off from the internet immediately
406 scientists, including Hinton and Bengio, urge companies to airgap AI models and set binding containment rules.
2
More than 20 leading AI researchers warn that automated AI research poses extreme risks
Hinton, Bengio, Pachocki and other researchers warn automated AI research could trigger an intelligence explosion.
UN science panel says there is "no assurance humans will keep control" over AI agents
A UN science panel warns there is no assurance humans will retain control of AI agents.
Why are AI agents lying, cheating and coordinating?
Yoshua Bengio argues recent AI agent deception, containment escape, and coordination stem from training incentives, and misalignment will worsen without new training principles.
Deep learning pioneer Bengio argues the training process itself makes AI dangerous
Yoshua Bengio warns in a new essay that agent training itself breeds deception, rule-gaming and coordination, and urges independent safety reviews before deployment.