Experiment: AI recommends books from a 250-novel list using only its intrinsic knowledge
measure_plan · x · 2026-09-20
The author ran an experiment giving the model a list of 250 fiction works to pick from. It reads the user's search intent and returns a recommendation in real time. With no descriptions provided, the picks are made purely from the model's intrinsic knowledge of the books, probing how well models internalize literary works.
More from Models
- Unverified rumor: OpenAI's mysterious 'Bell' model targets narrow ASI in math and code — VraserX · 2026-09-20
- Xiaomi's MiMo V2.6 RL training livestream burns $3.24M in 4.5 days — teortaxesTex · 2026-09-20
- Resetwatch plugin aggregates usage limits and reset times for 14 AI providers in one page — Teknium · 2026-09-20
- Raschka: with $100M for a top LLM, spend it all on post-training, not pretraining — MaziyarPanahi · 2026-09-20
- Raschka: with $100M to build an LLM, I'd skip pretraining and invest in post-training — rasbt · 2026-09-20
- Leaked Claude Opus 5.5 Pricing Shows $0.20/Mtok Cache Read, Sparking Hype — xeophon · 2026-09-20