HN Explorer

offaxis

↗ HN profile [ 68.3 ms ] full profile
Karma
0
Created
()
Submissions
0
  1. 1 points 0
  2. How to keep what the model makes up out of the agent (github.com)
    1 points 0
  3. We gave AI a trust we never gave people: can it, may it, on what grounds (discuss.huggingface.co)
    1 points 1
  4. Values, conditions, intent: People should declare them, not the model (github.com)
    1 points 0
  5. LLM Tool Failures: Only 3 Root Causes – Value, Condition, Intent (github.com)
    1 points 1
  6. Forms did five things. Natural language kept one

    A form did five things at once: judged the condition, picked which form to open, took the values, carried where each value came from, and validated the required fields. Natural language kept the third one and gave the…

    3 points 0
  7. 1 points 0
  8. From knowledge-based inference to presence-based verification (discuss.huggingface.co)
    2 points 0
  9. 1 points 0
  10. If Unsure, Ask. Never Guess. AI Agent Pre-Execution Checklist (discuss.huggingface.co)
    2 points 0
  11. Unknown Is Not False: An AI Agent Pre-Execution Checklist (discuss.huggingface.co)
    3 points 1