RL-trained LLMs have functionally infinite search space, replies Jack Clark
menhguin · x · 2026-09-20
Jack Clark calls "stochastic parrot" a mimetically-fit cognitive virus (2021-2025) that blinded many to AI progress. @menhguin counters that while pretrained LLMs may literally be stochastic parrots, once RL'd on queries with an effectively infinite input space of queries and retrieved context, the search space becomes functionally infinite — inputs are out-of-distribution, yielding novel OOD trajectories.
More from AGI Musings
- Agents' bottleneck isn't intelligence but goal commitment — and that's good for alignment — mimi10v3 · 2026-11-12
- Google Cloud survey: 78% say legacy enterprise vendors may not lead the AI era — rseroter · 2026-11-12
- Safety researchers blast OpenAI/Anthropic plan: automating alignment research with possibly misaligned AI — trevposts · 2026-11-12
- NYT essay: resisting Big Tech and AI takes collective action, not willpower — TuhinChakr · 2026-11-12
- Ethan Mollick: 'talk to your documents' RAG solutions already feel dated — emollick · 2026-11-12
- Anthropic's pitch hasn't changed in 5 years: 'AI is winner-take-all, we will build god' — menhguin · 2026-11-12