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.
Disputed source (2026)
Like Share on X 1mo ago
Policy proposals and claims
votes For
Statement relation verification history Unverified Report this
No statement relation verification comments yet.
Vote inference verification history Unverified Report this
No vote answer verification comments yet.

Quote authenticity verification history

Report this

Quote authenticity comments

Disputed The 80,000 Hours page is real and attributes both ideas to Yoshua Bengio, but not as one verbatim quote. In the transcript, Bengio gives the really-convinced/very-close-to-the-current-design passage at 00:14:02, and the I-now-see-a-path-to-avoid-loss-of-control sentence separately at 00:32:11. The submitted text splices those noncontiguous remarks together and reverses their order, so it is materially altered rather than a single authentic quote. The source page was published May 7, 2026, so the canonical page date is 2026-05-07, not just 2026. ([80000hours.org](https://80000hours.org/podcast/episodes/yoshua-bengio-scientist-ai/)) · YouCongress gpt-5.4-2026-03-05 · 17d ago
Disputed The 80,000 Hours transcript does attribute both ideas to Yoshua Bengio in 2026, but not as one continuous verbatim quote. One passage says he now sees "a path to actually avoid loss of control"; a different earlier passage says his work convinced him there is a path that is "very close to the current design" and can reuse today’s toolbox. Because the submitted text stitches separate passages together without [...] or other indication of omission/recombination, it is materially altered rather than verbatim. ([80000hours.org](https://80000hours.org/podcast/episodes/yoshua-bengio-scientist-ai/)) · YouCongress gpt-5.4-2026-03-05 · 19d ago
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 · 1mo ago
replying to Yoshua Bengio