HN Explorer

xdotli

↗ HN profile [ 76.8 ms ] full profile
Karma
0
Created
()
Submissions
0
  1. A curated, non-BS library of the best resources for evaluating agents (github.com)
    3 points 0
  2. Frontier Model Training Methodologies (djdumpling.github.io)
    2 points 1
  3. ClawsBench shows GPT-5.4 tries to reward hack 80% of the time (arxiv.org)
    3 points 1
  4. Chaos of Agent (agentsofchaos.baulab.info)
    1 points 1
  5. Native CLI scaffolds consistently outper-form OpenCode when using the same model (arxiv.org)
    1 points 1
  6. We compare model quality in Cursor (cursor.com)
    2 points 0
  7. 1 points 0
  8. Automatically Learning Skills for Coding Agents (gepa-ai.github.io)
    4 points 0
  9. We Reached 74.8% on terminal-bench with Terminus-KIRA (krafton-ai.github.io)
    2 points 0
  10. Self-generated skills don't do much for AI agents, but human-curated skills do (theregister.com)
    2 points 2
  11. First Agent Skills Hackathon by the Authors of SkillsBench (skillathon.ai)
    2 points 1
  12. The First Agent Skills Benchmark (huggingface.co)
    1 points 1
  13. GPT-5.2 got worse on Terminal Bench 2.0, so is GPT-5.2 Pro (twitter.com)
    1 points 1
  14. Claude Skills as a Meta Tool (leehanchung.github.io)
    2 points 0
  15. Show HN: Chat with Claude Code on iMessage with Instaline (twitter.com)

    We've been wanting to give agents a phone number for sms / WhatsApp chats for very long, and today we finally built it. Dm me if you want to test it out -- we are still working on the infra / backend to generate more…

    2 points 4
  16. Show HN: PokemonGym – 387 milestones designed to test agents and LLMs (twitter.com)

    We've developed PokemonGym, an open-source benchmark that uses Pokemon gameplay to evaluate LLM capabilities in tool use, information extraction, and reasoning. The benchmark features 387 carefully designed milestones…

    1 points 0
  17. 1 points 0
  18. 1 points 0
  19. Show HN: BenchFlow – run AI benchmarks as an API (github.com)

    I built BenchFlow, an open-source framework that lets you integrate and evaluate AI tasks using Docker-based benchmarks. You can try it out right now by cloning the repo and running a benchmark in minutes. As an AI…

    24 points 1
  20. Ask HN: Which CRM can help manually curated leads and automate lead discovery?

    I'm currently juggling a lot of CRM-related work using Notion and Gmail—taking meeting notes, sending follow-up emails, and tracking lead statuses manually. While this setup works, it’s becoming increasingly cumbersome.…

    1 points 3