Tutorials

Thank you to @robertwiblin for inviting me on the @80000Hours podcast to discuss the research progress we’re making at @LawZero_ to create s…

Thank you to @robertwiblin for inviting me on the @80000Hours podcast to discuss the research progress we’re making at @LawZero_ to create safe-by-design AI systems. Our current approach, Scientist AI

DGX agentx-post
tutorialsyoshua-bengio--x

Thank you to @robertwiblin for inviting me on the @80000Hours podcast to discuss the research progress we’re making at @LawZero_ to create safe-by-design AI systems. Our current approach, Scientist AI, makes me certain that we can find a technical path forward towards safe, reliable, and highly capable AI. Yoshua Bengio thinks he knows how to make provably safe superintelligent agents. Bengio built the foundations of modern AI and is the most cited living scientist. He believes his alternative training setup would: 1. Guarantee honesty 2. Prevent unintended goals 3. Produce capable…

Source: Yoshua Bengio (X) | 2026-05-08

Loading related sources…