HN Explorer

praneeth-v

↗ HN profile [ 12.8 ms ] full profile
Karma
0
Created
()
Submissions
0
  1. Show HN: Agent Action Guard – AI agent action safety

    Your agents can perform harmful actions without barriers. You do not know that yet. HarmActionBench experiments allowed AI agents to use tools based on harmful instructions, and the results are shocking. Even latest…

    2 points 0
  2. AI Agent action safety is not covered yet

    HarmActionBench experiments allowed AI agents to use tools based on harmful instructions, and the results are shocking. Even latest popular AI models, including GPT and Claude, scored very low. They have no barriers in…

    2 points 1