LoL maze experiments: hard-coded layer orders replicate specific search algorithms
micahgoldblum · x · 2026-11-04
Parts 5-6 of the thread: maze experiment setup — trained on mazes solved 5 ways, then hard-coding layer orders matching a single algorithm makes the model execute it >99.7% of the time.
More from Research
- 20-40% of alignment data is noisy: a loss-reduction scoring framework to fix it — burkov · 2026-11-04
- Scientists image quantum entangled photons in real time, and the result looks like a taijitu — CurieuxExplorer · 2026-11-04
- kalomaze: crude diffusion autoencoders may lose low-frequency info at the latent stage — kalomaze · 2026-11-04
- Structured captions boost text-to-music alignment, new Music DSG metric beats CLAP — affige_yang · 2026-11-04
- Fruit fly's 166,000-neuron circuit map is being used to drive robot behavior — CurieuxExplorer · 2026-11-04
- Orbital engineers use AI OS CurieOS to draft two-phase cold plate designs — TimothyDuignan · 2026-11-04