MIT team finds a literal map of the world inside Llama-2's activations
burny_tech · x · 2026-10-29
- Wes Grote, working with Max Tegmark, released a new paper asking whether language models have an internal world model and a sense of time across multiple spatiotemporal scales.
- The team claims they do, presenting evidence of a literal map of the world found inside Llama-2's activations.
- The result is empirical progress on the "stochastic parrot" debate: LLMs appear to encode structured representations of the external world internally.
More from Research
- Preprint: Human peer reviewers caught only 27% of major errors, all 15 AI models beat them (53-96%) — anshulkundaje · 2026-10-29
- New paper rules out Hamiltonian Phase States as a route to quantum-only Microcrypt — StefanoGogioso · 2026-10-29
- MSR AI for Science team hiring postdoc to generate molecular data for Skala — FrankNoeBerlin · 2026-10-29
- ML-enhanced resonant soft X-ray scattering enables sub-monolayer tracking of buried-interface molecular states — carbon-lab · 2026-10-29
- Any3R: one feedforward model handles 13 camera types for 3D reconstruction, beating OmniVGGT and PanoVGGT — zhenjun_zhao · 2026-10-29
- GeoGSplat: geometry priors top DTU and NRGBD with just 65K Gaussians — zhenjun_zhao · 2026-10-29