Summary of "Language Models are Few-Shot Learners"

SPADE lets a single LLM both write executable training environments and solve them, achieving +8.1 average improvement over base on eight held-out benchmarks via hint-based regret self-play.

EvoMem's persistent memory of successful mutation strategies yields a 6.40% average performance gain and 5.93x speedup in LLM-based evolutionary code search.

COBS stores compressed per-block key covariances to raise block sparse attention selection from first-order to second-order approximations, closing 86% of the gap to dense attention with minimal extra KV cache reads.