@ClementDelangue: We need open traces so that everyone can train open agent models! cc @steipete @badlogicgames @thdxr @matanSF @hwchase17
Summary
Clement Delangue advocates for open traces to democratize training of open agent models.
View Cached Full Text
Cached at: 04/22/26, 07:06 PM
We need open traces so that everyone can train open agent models! cc @steipete @badlogicgames @thdxr @matanSF @hwchase17
Similar Articles
@ClementDelangue: Should we try to train an open source AI building model? We obviously have interesting datasets with HF, MLintern, tran…
Clement Delangue asks whether an open source AI building model should be trained, noting available datasets and tools like HF, MLintern, transformers, and trl.
@julien_c: Today I'm launching a new project called SynthTraces It is a minimal codebase to generate synthetic coding agent sessio…
Julien Chaumond launches SynthTraces, a minimal codebase that generates synthetic coding agent session traces by having an open model (via HF Inference Providers) interact with a small local model (via llama.cpp) on real open-source codebases, producing over 2,000 Pi session traces for training and fine-tuning LLMs.
@adithya_s_k: You can now finetune models on agent traces directly with TRL Claude Code traces Codex traces OpenClaw traces Pi traces…
TRL now supports fine-tuning models on agent traces from various sources like Claude Code, Codex, OpenClaw, and Pi, moving towards a standardized stack for training agentic models.
@ClementDelangue: How? Instead of closed-source frontier labs running the same training runs in secret and siloes, open science and open-…
Clement Delangue argues that open science and open-source AI can make AI spending more efficient, contrasting US and China's AI investment strategies.
@martin_casado: This tackles a very hard, very important problem in AI systems. Basically how do you expose your traces at scale to age…
A tweet by Martin Casado highlighting a solution to the difficult problem of exposing traces at scale to AI agents, balancing cost and AI leverage.