One topic. Every takeSeek and you shall find

Reading up on llm-training

1 deep · digging since oct 16

  • ianbarber.blog favicon
    Mo’ turns, mo’ problems – Ian’s Blog

    Training agentic LLMs with RL suffers off‑policy drift from harness variations, tool‑call formatting, long rollouts, and training‑inference kernel mismatches, needing extra computation or approximations for correct updates.

read later

For all the tabs you promised to read.
Save to read. Read to clear.

Close tabs. Keep links.