HN Explorer

ratnaditya

↗ HN profile [ 29.7 ms ] full profile
Karma
0
Created
()
Submissions
0
  1. 1 points 1
  2. Prompt eval cues predicted refusal shifts across 32k LLM rollouts (medium.com)
    1 points 1
  3. 13 points 2
  4. 1 points 0
  5. Show HN: AgentWard – After an AI agent deleted files, I built a runtime enforcer (github.com)

    I've spent time working on AI safety and kept running into the same problem: AI agents have far more access than they need, and the only thing stopping them from misusing it is a prompt. Prompts can be ignored. They can…

    1 points 1