HN Explorer

thejash

↗ HN profile [ 75.3 ms ] full profile
Karma
0
Created
()
Submissions
0
  1. 1 points 1
  2. How Offload Works: Inside the Rust CLI that sped up our tests by 6x (imbue.com)
    12 points 0
  3. A case study in testing with 100+ Claude agents in parallel (imbue.com)
    68 points 9
  4. Usefully run 100s of Claudes in parallel with mngr (imbue.com)
    21 points 0
  5. Software as Bonsai (substack.com)
    2 points 0
  6. AI should be Free Software (substack.com)
    3 points 0
  7. Why agents matter more than other AI (substack.com)
    1 points 1
  8. What's needed for AI agents to work (substack.com)
    2 points 1
  9. Decentralization or Dystopia: Pick 1 (substack.com)
    1 points 0
  10. Show HN: Sculptor – A UI for Claude Code (imbue.com)

    Hey, I'm Josh, cofounder of Imbue. We built Sculptor because we wanted a great UI for parallel coding agents. We love Claude Code, but wanted to solve some of the problems that come from running multiple agents in…

    176 points 49
  11. Sculptor: Catch and fix issues as you code (imbue.com)
    61 points 3
  12. Carbs, a hyperparameter optimizer that scales small experiments to LLMs (imbue.com)
    4 points 1
  13. Open-source, sanitized evaluation datasets for models that reason and code (imbue.com)
    3 points 1
  14. Infrastructure setup and open-source scripts to train 70B model from bare metal (imbue.com)
    325 points 43
  15. 1 points 0
  16. Scaling Laws for Every Hyperparameter via Cost-Aware HPO (generallyintelligent.com)
    3 points 0
  17. Jim Fan, Nvidia: On foundation models for embodied agents and scaling data (generallyintelligent.com)
    2 points 1
  18. 1 points 0
  19. Noam Brown, FAIR: On achieving human-level performance in Diplomacy, and more (generallyintelligent.com)
    1 points 1
  20. Nicklas Hansen, UCSD: On long-horizon planning and much more (generallyintelligent.com)
    1 points 1
  21. Jack Parker-Holder, DeepMind: On open-endedness, offline learning, and much more (generallyintelligent.com)
    1 points 1
  22. Chelsea Finn, Stanford: On the biggest bottlenecks in robotics and RL (generallyintelligent.com)
    1 points 1
  23. Hattie Zhou, Mila, on supermasks, iterative learning, and fortuitous forgetting (generallyintelligent.ai)
    3 points 1
  24. Generative AI startups we want to fund (outsetcapital.com)
    1 points 0
  25. Minqi Jiang, UCL, on environment and curriculum design for general RL agents (generallyintelligent.ai)
    2 points 1