Claude 1d3cca1e76 docs/research: track that the first harness landed differs from proposed shape ... The note proposed surface 1 (index-build tuning) with recall@K oracle and BauplanLabs evolutionary tournament as the "smallest experiment that would produce signal." What landed at research/lance-autoresearch/ is a different shape: PQ kernel optimization with bit-exact correctness oracle and Karpathy single-agent autoresearch loop. Add a "First implementation landed" section that records the divergence and the reasoning (seconds-scale eval favors the autoresearch shape; kernel work has a more direct upstream PR path; the bit-exact oracle removes dataset-overfitting incentive). Bumps the note to revision 3. scripts/check-agents-md.sh still passes (30/30 links). https://claude.ai/code/session_01Aq8kBUcjmEPobcEufnWbW5		2026-05-14 23:32:57 +00:00
..
llm-evolutionary-sampling.md	docs/research: track that the first harness landed differs from proposed shape	2026-05-14 23:32:57 +00:00