HN Explorer

vrm

↗ HN profile [ 588 ms ] full profile
Karma
0
Created
()
Submissions
0
  1. ATLAS: Autoformalized Textbook Library At Scale (github.com)

    https://twitter.com/arnal_charles/status/2060009395107377282, https://xcancel.com/arnal_charles/status/2060009395107377282 Paper: Formalizing Mathematics at Scale - https://arxiv.org/abs/2605.29955

    32 points 4
  2. Stop comparing price per million tokens: the hidden LLM API costs (tensorzero.com)
    3 points 2
  3. Ask HN: What do you recommend for test observability?

    I maintain an OSS project with a very involved CI setup. We're at the point where it is worth having observability into which tests are flaky, especially within intra-test-run retries. An ideal solution would be a…

    3 points 0
  4. Improving Cursor Tab with RL (cursor.com)
    6 points 0
  5. Automatically Evaluating AI Coding Assistants with Each Git Commit (tensorzero.com)
    3 points 0
  6. Wider or Deeper? Scaling LLM Inference-Time Compute with Adaptive Tree Search (arxiv.org)
    3 points 0
  7. Think of LLM Applications as POMDPs – Not Agents (tensorzero.com)
    2 points 0
  8. An experimental design perspective on model-based reinforcement learning (blog.ml.cmu.edu)
    3 points 0
  9. Spinlaunch with Basic Physics [pdf] (virajrmehta.com)
    2 points 2
  10. Data breach allowed Stanford applicants to view others’ information (stanforddaily.com)
    9 points 0
  11. Elon Musk Invents World's Costliest, Worst Subway (theconcourse.deadspin.com)
    1 points 0
  12. Simple Random Search provides a competitive approach to RL (arxiv.org)
    2 points 0