Andrew Lampinen on where RL creativity ends: is connecting two known math fields a new discovery?
AndrewLampinen · x · 2026-10-03
Continuing the debate on what RL teaches, Andrew Lampinen argues RL can certainly discover genuinely new things — but the boundary is not always clear. He poses a sharp example: if a model connects two areas of mathematics that have never been linked before, is that "new" or "old" if both areas already appeared in training? The question cuts to the core of whether RL merely amplifies training data or produces real novelty.
Related event: DeepMind Researcher Debates Neurosymbolic Camp on LLM Math Limits(4 posts)→
More from AGI Musings
- Harvard physicist used open-source BootLoops and Claude to produce 36 manuscripts in 3 months — The Decoder · 2026-10-03
- An AGI bar: a single model competing professionally across esports, in real time — Turbulent-Step-3207 · 2026-10-03
- Jon Barron Rallies 'Team Meatbag' Against Rising Moral Status for AI Checkpoints — IsForAt · 2026-10-03
- Music industry fears AI eating existing revenue, struggles to imagine new markets it could create — jordiponsdotme · 2026-10-03
- AI bubble may burst, but the technology is here to stay, argues 25-year computing veteran — SprayPuzzleheaded115 · 2026-10-03
- Digital beings moral status debate: 'shut up and multiply' vs Timnit Gebru's pushback — mjdramstead · 2026-10-03