LLMs show "insane regression" in intelligence when discussing cell therapy, says blogger
owl_posting · x · 2026-11-09
Blogger owlposting reports an "absolutely insane regression" in LLM intelligence once conversations turn to cell therapy: the models fumble badly and produce incoherent outputs, which he describes as "spaghetti falling out of their pockets" behavior.
His explanation: humans themselves don't really understand what's happening in this field, so training data is thin—and "it turns out superintelligence feels similarly," suggesting the weakness reflects the scarcity of solid domain knowledge rather than a model-specific bug.
More from Models
- Mistral Large 4 lands: 1.05T-param MoE, best Western open weights but only mid-pack — maier_ak · 2026-11-09
- ChatGPT-User crawls drop 81% as OpenAI shifts to its own index — gaganghotra_ · 2026-11-09
- Simon Willison: Claude Opus 5.5 Ports Three.js 3D Scene to Vanilla JS + WebGL — Simon Willison · 2026-11-09
- Grok's Legacy Plan Is Extremely Generous: Heavy Daily Use Barely Hits 30% Quota — op7418 · 2026-11-09
- Together AI: leaderboards are for shortlisting, your production traffic is the real benchmark — togethercompute · 2026-11-09
- Gemini quietly reads your Android messages, calls and Gmail — here's how to limit it — Med1_Ai · 2026-11-09