'Hand-writing weights' is just searching learned optimizers, cites Sohl-Dickstein talk
akbirthko · x · 2026-11-04
akbirthko argues that "hand-writing weights" is essentially program searching over learned optimizers, recommending Jascha Sohl-Dickstein's (Google Brain) MIT CSL seminar "Learned optimizers: why they're the future, why they're hard, and what they can do now", streamed by the MIT Improbable AI Group with 1K+ views.
More from Research
- Weight-editing author: gains aren't real knowledge — Gemma math didn't improve, but Qwen3 issue is real — lateinteraction · 2026-11-04
- rasbt questions Qwen3 weight-editing gains: 50 GRPO steps already lift MATH-500 from ~15% to ~50% — rasbt · 2026-11-04
- NVIDIA releases Dory1.0-4B, a looped recurrent LM beating larger models — nvidia · 2026-11-04
- Running controlled LLM experiments with Codex CLI: disable every tool via config — lateinteraction · 2026-11-04
- Claude Opus 5 surgically edits ~1% of ProteinMPNN weights into SolubleMPNN-like behavior — AllThingsApx · 2026-11-04
- ESMFold author: AlphaFold-style covariation could unlock small-molecule prediction — sokrypton · 2026-11-04