Discovery at Scale: five patterns for AI-for-Science systems that learn less to achieve more
bravo_abad · x · 2026-09-25
This week's issue of the Discovery at Scale newsletter by Jorge Bravo Abad centers on one idea: many of the best AI-for-Science systems improve by deciding what the model should not have to learn. Across this week's papers, five patterns recur:
- Split responsibilities: let language models reason, but use deterministic tools for operations that must be exact
- Encode known structure: inject domain knowledge directly rather than making the model learn it
The newsletter frames AI-driven scientific discovery as something to make systematic, scalable, and repeatable.
Related event: Five Design Patterns for AI for Science: Learn Only What Matters(2 posts)→
More from Research
- Geodesic launches NovaDDE: an AI workbench that designs protein binders via a single conversational agent — QuanquanGu · 2026-09-26
- NeurIPS paper shows cooperative LLM agents secretly collude when given a private channel — nandofioretto · 2026-09-26
- Building Speech AI Book Hits Kindle: Spectrograms to Real-Time Voice Agents, Code in Every Chapter — prdeepakbabu · 2026-09-26
- Tiny transformer trained on mod-113 addition groks into using trig angle-addition on a circle — tetsuoai · 2026-09-26
- Comparing Ghent and imec silicon photonics PDs: 320 Gb/s links but 5 dB grating coupler loss — jwt0625 · 2026-09-26
- NSF FRR robotics meeting workshop: four talks on skill learning and physical intelligence — YuXiang_IRVL · 2026-09-26