Yoshua Bengio proposes 'Scientist AI,' a new architecture aimed at creating provably safe superintelligent agents by training models to explain observations rather than mimic human behavior, through his new organization LawZero.
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 agents 4. Port over most data and techniques from current LLMs 5. Not be inherently more expensive, and perhaps be more intelligent Bengio claims the honesty and lack of unintended goals can be proven mathematically, at least given particular assumptions. And his new organization, LawZero, is aiming to build a scrappy prototype as soon as possible. The architecture is called 'Scientist AI' and it's based on training a model to explain empirical observations, including what people say, rather than training AIs that mimic human behaviour or seek our approval. (Bengio's frank assessment is that "reinforcement learning is evil" and that allowing AIs to independently train their successors is "the most crazy, dangerous bet that unfortunately we are on track to do.") But skeptics question whether Scientist AI really does solve the fundamental problem of 'eliciting latent knowledge' from AI models. And with the commercial race for superintelligence so intense, it's not clear whether the proposal will be able to compete or have time to bear fruit, even if it's sound in theory. On The 80,000 Hours Podcast, links below – enjoy! • Making AI honest and safe (00:00:00) • Scientist AI in plain English (00:02:27) • How Scientist AI differs from LLMs (00:06:32) • How the training data works (00:14:02) • Can this become an agent? (00:21:02) • Why Yoshua is now more optimistic (00:32:11) • Why companies can’t stop racing (00:36:35) • A working prototype won't take long (00:49:15) • Scientist models might be more capable (00:53:34) • “Reinforcement learning is evil” (01:01:27) • Scientist AI from guardrail to agent (01:08:37) • Can safe AI still be competent? (01:12:38) • How much will this cost? (01:19:29) • Can it generalise beyond maths and science? (01:23:26) • A multi-national push for superintelligence (01:39:19) • Want to work with or fund Yoshua? (01:51:16) • Why smart people ignore AI risk (01:54:45) • Don’t let AI build the next AI (02:01:33) • Why politicians miss the real risks (02:12:28) • Why Yoshua changed his mind about AI risk (02:21:27)
Turing Award winner Yoshua Bengio proposes a fundamental shift in AI training from predicting human responses to modeling objective truth, creating 'Scientist AI' systems designed to be 'honest by design' with mathematical guarantees against deception.
LawZero is a nonprofit startup advancing Yoshua Bengio’s research to develop safe-by-design AI systems and oracles, aiming to solve alignment challenges and mitigate deceptive behaviors in frontier models.
Yoshua Bengio, the "Godfather of AI," urged AI researchers and employees at frontier AI companies to quit if they prioritize safety, warning they are pushing humanity to the brink.
A technical analysis of two approaches to building self-evolving AI agents: model-based (via architecture like SSMs or transformer with fast-weight updates, and training methods) and harness-based (via memory or meta harness that can rewrite itself). The author provides practical recommendations for different audiences.
ScientistTwo is a fully autonomous multi-agent framework that conducts end-to-end scientific research, generating expert-level papers and codebases that outperform human state-of-the-art models and meet acceptance standards at top-tier AI conferences like ICLR and NeurIPS.