Post-Training a 35B Open Model for Code Search: 100x Cheaper Than Frontier Models
ypatil125 · x · 2026-09-05
Applied Compute and turbopuffer published a technical writeup on making small open-weight models competitive at large-scale code search: they built an RL environment to post-train Qwen3.6-35B-A3B to use search tools over an index of 9,000 real GitHub repos, with narrow (deep, ≤1,000-repo corpora) and open-ended (broad) task types. At 300 repos the approach is 3x faster than filesystem + grep and cuts marginal search cost by up to 100x vs frontier models, topping the needle-in-a-haystack task — showing that targeted RL post-training plus a dedicated index beats frontier models' ls/grep habits at scale.
Related event: RL-Trained 35B Open Model Cuts Code Search Costs 100x(2 posts)→
More from coding & agent
- Bolt launches parallel task execution for faster dev workflows — tristanbob · 2026-09-05
- Open-source Claude Code course goes viral: 15 modules from first project to production — adnan_hashmi · 2026-09-05
- Agent Substrate brings instant suspend/resume and 10x density to K8s AI agents — davemccollough · 2026-09-05
- Caching Docker layers in Google Cloud Build to meaningfully speed up CI — rseroter · 2026-09-05
- Muse Spark 1.3 max released with significantly stronger coding and agentic performance — alexandr_wang · 2026-09-05
- Alexandr Wang Announces Muse Spark 1.3 Max With Stronger Coding and Agentic Performance — alexandr_wang · 2026-09-05