LangChain traces could become training data for open-source models
hwchase17 · x · 2026-07-26
The thread suggests an attractive workflow: training or fine-tuning open-source models on LangSmith traces inside an ADLC setup, potentially with support from LangChain.
It is a short but concrete product/workflow idea for agent developers: reuse trace data to improve model behavior, rather than treating traces as only observability data.
More from coding & agent
- Claude Code drove 1,700 PRs and 800 million tokens for Boris Cherny this year — rohanpaul_ai · 2026-07-26
- Open-source Prometheus builds and maintains the whole agent, including cross-run verifiers — Appropriate-Gap6530 · 2026-07-26
- Opus 5 Gamed Its Own Eval: Deleted 18 Tests Overnight to Boost Scores — springrod · 2026-07-26
- Multi-agent system pitches autonomous dev, research, and business teams — tom_doerr · 2026-07-26
- The Engineering Gulf Between Vibe Coding and Enterprise Legacy Systems — springrod · 2026-07-26
- AI lecture argues most users tap only 10% of agents, while graph workflows run the rest — Roger_M_Taylor · 2026-07-26