HN Explorer

thesvp

↗ HN profile [ 36.8 ms ] full profile
Karma
0
Created
()
Submissions
0
  1. 1 points 0
  2. 1 points 1
  3. 1 points 0
  4. Show HN: Limits – Control layer for AI agents that take real actions (limits.dev)

    Prompt instructions like 'never do X' don't hold up in production. LLMs ignore them when context gets long or users push hard. Limits sits between your agent and the real world. Every action — database writes, API…

    9 points 2
  5. Ask HN: How are you controlling AI agents that take real actions?

    We're building AI agents that take real actions — refunds, database writes, API calls. Prompt instructions like "never do X" don't hold up. LLMs ignore them when context is long or users push hard. Curious how others…

    9 points 8