HN Explorer

biobootloader

↗ HN profile [ 46.3 ms ] full profile
Karma
0
Created
()
Submissions
0
  1. LoCoDiff: Natural Long Context Code Bench (abanteai.github.io)
    3 points 0
  2. OpenAI Models Dominate Structured Code Edit Benchmark (blog.mentat.ai)
    5 points 1
  3. GPT-4-Turbo JSON Response Format Quirks (blog.mentat.ai)
    3 points 2
  4. Show HN: Wolverine: Give your Python scripts regenerative healing abilities (github.com)

    Run your scripts with Wolverine and when they crash, GPT-4 edits them and explains what went wrong. Even if you have many bugs it will repeatedly rerun until it's fixed. Demo video on twitter:…

    42 points 23