HN Explorer

Hiskias

↗ HN profile [ 52.7 ms ] full profile
Karma
0
Created
()
Submissions
0
  1. Show HN: Open-Source Lightweight Prompt Injection Safety (github.com)
    1 points 0
  2. Open Sourced R-Lens (github.com)
    1 points 0
  3. The Interpretability Illusion – Why we should train models to be interpretable (hisku.substack.com)
    1 points 0
  4. Show HN: Stop Babysitting Your Agents (github.com)
    2 points 0
  5. 1 points 0
  6. Training a 22MB prompt injection classifier that runs inline in a Lambda (stackone.com)
    3 points 3
  7. Stack-nudge – Stop babysitting your AI agent's terminal (github.com)
    1 points 0
  8. Training a 22MB prompt injection classifier (stackone.com)
    7 points 0
  9. Defender – Local prompt injection detection for AI agents (no API calls) (npmjs.com)
    2 points 0
  10. Defender – Local prompt injection detection for AI agents (no API calls) (npmjs.com)
    2 points 2