HN Explorer

agairola

↗ HN profile [ 37.1 ms ] full profile
Karma
0
Created
()
Submissions
0
  1. 1 points 0
  2. 1 points 0
  3. 1 points 0
  4. 1 points 0
  5. 1 points 0
  6. 1 points 0
  7. Claude 4.7 blocks cyber prompts: before the fact vs. after the fact (raxitlabs.com)
    2 points 0
  8. 1 points 0
  9. Show HN: 10-min AI threat model (STRIDE and MAESTRO), assumption-driven (raxit.ai)

    Hi HN, I built an assumption-driven AI security assessment for teams shipping AI features without a dedicated security team yet. You paste your AI use case (what it does, data types, vendors, deployment). In ~10 minutes…

    1 points 0
  10. Show HN: Securing the Ralph Wiggum Loop – DevSecOps for Autonomous Coding Agents (github.com)

    Hi HN, Since AutoGPT in 2023, I’ve been uneasy about fully unsupervised AI agents. I see the productivity upside, but “kick it off and walk away” felt risky. Recently, the “Ralph Wiggum loop” pattern has gone viral. The…

    4 points 0
  11. Did we solve AI agent identity in 2025? (raxit.ai)
    1 points 2
  12. We built an open benchmark to test GPT-5 "safe completion" (bench.raxit.ai)
    2 points 1