Top AI Papers of the Week: Self-Improvement Memory, Weight-Space Programming
dair_ai · x · 2026-11-22
dair-ai's weekly roundup (Nov 16-22) covers trending AI papers including AutoRL, EfficientSkill, Safe Personal RSI, CompoundingKernel, Self-Improvement Memory, Weight-Space Programming, and Self-Directed Self-Improvement. The Self-Improvement Memory work notes that harness optimization is usually studied with one fixed model and benchmark, and the optimizer must decide which parts of an evolved harness to keep when either changes.
More from Research
- AI reads 2,000 historical illustrations: individual errors, near-perfect aggregate patterns — _akpiper · 2026-11-23
- ReLU networks have zero second derivative almost everywhere — why PINNs need smooth activations — bravo_abad · 2026-11-22
- Sinclair lab uses AI to find chemical age-reversal molecules, mouse tissues rejuvenated in 4 weeks — thederbiedone · 2026-11-22
- Aaronson on reported LLM proof of the Riemann Hypothesis: 17.4M lines of Lean code — jedisct1 · 2026-11-22
- Tufazip losslessly compresses 1GB Wikipedia to 105MB, best neural-network-only entry on LTCB — RichmanRonald · 2026-11-22
- Fine-tuned 2B models beat OpenAI o3 and Gemini 2.5 few-shot on molecular classification — madeofAjala · 2026-11-22