Training a Specialist Code Search Agent with turbopuffer | Applied Compute
appliedcompute.com · 2,230 words · saved by 1 readers
How post-training and indexed retrieval make large-scale code search faster, cheaper, and more accurate.
Today’s frontier models are strong code searchers armed with nothing more than the tools a human would use: the filesystem, ls, and grep. That is usually enough on a single small repository, which is why coding agents generally use search tools that don't rely on a precomputed search index. However, this approach to code search becomes expensive and slow when the corpus is large. In these cases, savings from eschewing search indexes are offset by high inference costs for frontier models and slow grep tool calls. We partnered with turbopuffer to show how to solve both of these problems:…
saved by
related reading
- Understanding a Law Firm through Studyengram.com
- Machine Studying | Jacob Xiaochen Lijacobxli.com
- GitHub - karpathy/autoresearch: AI agents running research on single-GPU nanochat training automaticallygithub.com
- Composer2.pdfcursor.com
- Towards self-driving codebases · Cursorcursor.com
- PostTrainBenchposttrainbench.com
- Introducing SWE-grep and SWE-grep-mini: RL for Multi-Turn, Fast Context Retrieval | Cognitioncognition.ai
- Building a web search engine from scratch in two months with 3 billion neural embeddingsblog.wilsonl.in
- Fast regex search: indexing text for agent tools · Cursorcursor.com
- WebCode: Search Evals for Coding Agentsexa.ai
- Chroma Context-1: Training a Self-Editing Search Agent | Chromatrychroma.com
- >10x More Efficient Pretraining — Magicmagic.dev