HN Explorer

mustaphah

↗ HN profile [ 81.5 ms ] full profile
Karma
0
Created
()
Submissions
0
  1. Opportunity cost neglect (2009) [pdf] (bear.warrington.ufl.edu)
    2 points 0
  2. Economic Possibilities for our Grandchildren (1931) (fermatslibrary.com)
    1 points 1
  3. A field guide to Fable: finding your unknowns (twitter.com)
    1 points 1
  4. Ten Takeaways from the AI Engineering Report 2026: The Acceleration Whiplash (faros.ai)
    2 points 1
  5. The cost YAGNI was never about (newsletter.kentbeck.com)
    6 points 1
  6. Writing code vs. shipping code [pdf] (nber.org)
    3 points 0
  7. Trust Factory (newsletter.kentbeck.com)
    7 points 0
  8. LLMs pass a standard three-party Turing test (pnas.org)
    3 points 1
  9. The small sample trap in A/B testing (hadid.dev)
    4 points 1
  10. Tell HN: Claude two rate limits don't know about each other

    I was using Claude actively today right before my weekly limits reset. Weekly quota is now fresh - 0% used. But the session limit doesn't care. It's still at 100% from the previous session, so I'm locked out for another…

    2 points 0
  11. Enhancing gut-brain communication reversed cognitive decline in aging mice (med.stanford.edu)
    386 points 38
  12. Many SWE-bench-Passing PRs would not be merged (metr.org)
    278 points 34
  13. AGI is an unscientific myth (tandfonline.com)
    4 points 2
  14. Web Verbs (github.com)
    1 points 0
  15. OpenAI's 5-month experiment: building a product with no human-written code (openai.com)
    2 points 0
  16. SkillsBench: Benchmarking how well agent skills work across diverse tasks (arxiv.org)
    364 points 52
  17. Evaluating AGENTS.md: are they helpful for coding agents? (arxiv.org)
    232 points 44
  18. Curosr: Expanding our long-running agents research preview (cursor.com)
    3 points 0
  19. Measuring Time Horizon Using Claude Code and Codex (metr.org)
    1 points 0
  20. SWE-ContextBench: context learning benchmark in coding (arxiv.org)
    1 points 0
  21. SWE-AGI: benchmarking spec-driven software construction (arxiv.org)
    1 points 1
  22. Code Formatting Silently Consumes Your LLM Budget (arxiv.org)
    1 points 0
  23. Agent Trace by Cursor: open spec for tracking AI-generated code (agent-trace.dev)
    1 points 0
  24. METR releases Time Horizon 1.1 with 34% more tasks (metr.org)
    1 points 0
  25. Coffee timing isn't one-size-fits-all (examine.com)
    4 points 0