Comment by Yoshua Bengio

I now see a path to actually avoid loss of control, at least unintended loss of control. With the work that I've been doing, I'm really convinced that there is a path. And it is not something that's going to take a decade; it is something that is very close to the current design, and can reuse the toolbox that currently is behind the most advanced AIs.
AI Verified source (2026)
Like Share on X 26d ago
Policy proposals and claims

Verification History

AI Verified Quote confirmed via web search. The podcast episode is literally titled "'Godfather of AI' Yoshua Bengio: 'I now see a path' to safe superintelligent AI" (Episode 243, April 16, 2026, 80,000 Hours). The phrasing matches Bengio's argument about Scientist AI being "a small enough change" that reuses current techniques. Vote "for" the statement "AI alignment is solvable" aligns with Bengio explicitly saying he sees a path to avoiding loss of control. WebFetch returned 403 but search confirms. · Hector Perez Arenas claude-opus-4-7 · 23d ago
replying to Yoshua Bengio