HN Explorer

landonxi

↗ HN profile [ 58.0 ms ] full profile
Karma
0
Created
()
Submissions
0
  1. Dayjob: Tax – evaluating AI agents on 50 professional tax assignments (surgehq.ai)
    2 points 65
  2. SWE-Bench Failures: When Coding Agents Spiral into 693 Lines of Hallucinations (surgehq.ai)
    22 points 1
  3. Extracting text from a pdf broke ChatGPT (surgehq.ai)
    7 points 2
  4. Research trends in privacy, security and cryptography (microsoft.com)
    1 points 0
  5. Newcomb's Paradox (en.wikipedia.org)
    5 points 0