HN Explorer

kumama

↗ HN profile [ 32.2 ms ] full profile
Karma
0
Created
()
Submissions
0
  1. Designing dev onboarding for an agent-first world (castform.com)
    2 points 0
  2. I post-trained a model to reliably roll a die (castform.com)
    2 points 0
  3. Open-Weight Models Don't Need to Win (twitter.com)
    5 points 5
  4. Prompt caching but for RL – 7.5x speedup on long-prompt/short-response workloads (castform.com)
    4 points 0
  5. Pokegents: Making multi-agent coding feel like a team (castform.com)
    8 points 1
  6. Grpo explained: group relative policy optimization for LLM finetuning (cgft.io)
    1 points 0
  7. Do RL on a model with your vector db (cgft.io)
    1 points 0
  8. What is reinforcement learning finetuning (youtube.com)
    3 points 0
  9. RAG to riches: synthetic data for training RAG agents (cgft.io)
    2 points 1
  10. rag not lag: rl for fast agentic retrieval (cgft.io)
    3 points 0
  11. Show HN: Benchmax, a new open-source RL environment framework for LLM finetuning (github.com)

    Hello HN! I’ve been working on `benchmax`, a open-source framework for building, running, and parallelizing environments, to fine-tune LLMs with reinforcement learning. What I wanted to solve for: - Environments are…

    1 points 0
  12. Beating o3/o4-mini with Codebase-specific Reinforcement Learning (cgft.io)
    3 points 0
  13. We might be overestimating coding agent performance on SWE-Bench (cgft.io)
    1 points 1
  14. How to Improve Code Completion LLMs with Repo-Specific Finetuning (cgft.io)
    3 points 1
  15. Show HN: Free AI Code Completion for Xcode with model choice/codebase context (cgft.io)

    Download link: https://www.cgft.io/xcode Here are a few reasons to give this a shot, compared to others (e.g. Apple’s Swift prediction): Model Choice Use any local model you prefer through Ollama, or opt for our…

    2 points 0