sokrypton shows models can reason about which beta sheets interact
sokrypton · x · 2026-11-18
sokrypton shares a follow-up experiment: models appear pretty good at reasoning about which beta sheets interact. He notes the structure part is a gimmick—once you have a good contact map, converting it into a structure is trivial. Ubiquitin had among the most accurate contact predictions, so he converted it into a structure demo, with links to other proteins.
More from Research
- MLCB takeaway: agentic science is booming, with plenty of open questions — jmschreiber91 · 2026-11-18
- OpenAI study: persona-style CoT training drops monitorability from 0.94 to 0.22 — dair_ai · 2026-11-18
- LLM protein-folding test on fresh PDB entry lands near-random structures — MoAlQuraishi · 2026-11-18
- Lean-PEP turns worst-case optimization bounds into formally verified Lean proofs — prof_grimmer · 2026-11-18
- Two arms, two token streams, one shared vocabulary: new robot manipulation work open-sourced — DJiafei · 2026-11-18
- NUS's BiCAT action tokenizer for bimanual robots: 113/150 real-robot wins, 2.7x lower latency than OAT — DJiafei · 2026-11-18