HN Explorer

galsapir

↗ HN profile [ 85.3 ms ] full profile
Karma
0
Created
()
Submissions
0
  1. Creative Reading: Scaffolding Reading for Transformation (arxiv.org)
    1 points 0
  2. No agents after 8 pm (sparsethought.com)
    1 points 0
  3. AI Has Plunged the Book Publishing Industry into Utter Chaos (wsj.com)
    4 points 18
  4. Can AI agents conduct open-ended AI research? (arxiv.org)
    4 points 0
  5. Ask HN: Any Good Pi.dev Setups?

    trying to find the best setup for me. wondering if anyone has a preferred 'harness mode' for it.

    3 points 1
  6. Giving a domain a hill to climb: benchmarking as data activation (sparsethought.com)
    12 points 5
  7. A bitter lesson for medicine, or a benchmark problem? (sparsethought.com)
    2 points 0
  8. Can LLMs Beat Classical Hyperparameter Optimization Algorithms? (arxiv.org)
    120 points 11
  9. Gemma 4 E4B as a primary local LLM (replaced Qwen) (digg.com)
    2 points 0
  10. PEEK: Give Your Agent an Orientation Cache (MIT CSAIL, Khattab group) (zhuohangu.github.io)
    3 points 0
  11. Hyperagents (Meta Research) (arxiv.org)
    2 points 0
  12. The Unreasonable Effectiveness of HTML (claude.com)
    3 points 2
  13. 1 points 0
  14. The Comparator in Clinical AI (sparsethought.com)
    2 points 1
  15. Borges' cartographers and the tacit skill of reading LM output (galsapir.github.io)
    40 points 5
  16. 1 points 0
  17. Best read of 2026 so far was written in 1880 (galsapir.github.io)
    1 points 1
  18. Anthropic launched community ambassador program (claude.com)
    1 points 0
  19. LLMs as nudging research towards luke-warm middle (nature.com)
    1 points 0
  20. 1 points 0
  21. 1 points 0
  22. 1 points 0
  23. 1 points 0
  24. 1 points 0
  25. How do you evaluate a foundation model before you know what it's for? (galsapir.github.io)
    1 points 1