RicursiveAI claims 16x compute efficiency gain on code pretraining vs Olmo 3 baseline
samiramanabi · x · 2026-11-05
RicursiveAI reports a 16x compute efficiency win on code pretraining relative to its Olmo 3 baseline, achieved through improvements in scaling laws, model architecture, and data. The reposter quips "Data is all you need?", pushing back on pure data-scaling narratives.
More from Models
- ScreamingFace launches leaderboards showing multi-model systems can beat the best single model inside them — iamtrask · 2026-11-05
- OpenMined launches ScreamingFace: open-source model fusions beat best single models on live leaderboards — iamtrask · 2026-11-05
- DeepSeek 4.1 Flash impresses dev: 641M tokens cost just $4 — jasonkneen · 2026-11-05
- Claude Code screenshot shows Opus 5.5 with five reasoning-effort tiers and mid-session model switching — sergeykarayev · 2026-11-05
- Qwen-powered uni-robot-agent hits 31.39 on RoboDojo, beating GPT-6 Astra at 1/19.5 the cost — dotey · 2026-11-05
- Claude halts mid-task to interrogate an 'A3.5' arm it never defined — unusual LLM self-audit — teortaxesTex · 2026-11-05