Hacker News

New stories

Live mirror
30 storiesupdated just nowView source snapshot
  1. An Open-Source Terminal UI for Azure DevOps
    1 pointsby 1 minute ago
    —discuss
  2. What's Behind the AI Panic (bombthrower.com)
    1 pointsby 3 minutes ago
    —discuss
  3. The dataset where fine-tuning turned actively harmful – and how we now catch it (cacheverifier.com)
    1 pointsby 4 minutes ago
    —discuss
  4. Hackers Jailbreak AI Chatbots (twitter.com/hamzaonchain)
    1 pointsby 5 minutes ago
    —discuss
  5. CVE-2026-85706 (CVSS 10.0) (twitter.com/eqstlab)
    1 pointsby 6 minutes ago
    1comments
  6. Suicides in 5 Weeks. What's Going on at Cyber Command at Fort Meade? (thebanner.com)
    1 pointsby 8 minutes ago
    —discuss
  7. What 1,350 Runs Taught Us About Prompt Guardrails (humanbound.ai)
    1 pointsby 13 minutes ago
    —discuss
  8. CSV Lint update (Notepad++) text data syntax highlighting and quality validation (github.com/bdr76)
    1 pointsby 13 minutes ago
    1comments
  9. Uncensored and Offensive Security AI Models Benchmark (github.com/joasasantos)
    1 pointsby 15 minutes ago
    —discuss
  10. The Glimmer in Our Eye (With Grant Sanderson) Podcast (youtube.com)
    1 pointsby 16 minutes ago
    —discuss
  11. Cue – Your Personal Agents, with Their Own Identity (cue.im)
    1 pointsby 16 minutes ago
    1comments
  12. Show HN: I wired a fruit fly connectome to play tic-tac-toe (github.com/50rishu)
    1 pointsby 16 minutes ago
    1comments
  13. Show HN: Open-source skills for end-to-end video ad campaigns (github.com/supercmohq)
    2 pointsby 20 minutes ago
    —discuss
  14. Aw1-breaker: Sub-millisecond execution circuit breaker for AI agents (github.com/mvikmanners)
    1 pointsby 22 minutes ago
    —discuss
  15. Show HN: PocketUni – A mobile app for discovering universities (play.google.com)
    1 pointsby 23 minutes ago
    —discuss
  16. OpenAI halts frontier training over rogue models (stork.ai)
    2 pointsby 28 minutes ago
    1comments
  17. Terminal Velocity for Claude Code. Tickets, Loops, Focus. All in One (github.com/quazardous)
    1 pointsby 29 minutes ago
    —discuss
  18. A Rich Neighbor Named Xerox (folklore.org)
    1 pointsby 31 minutes ago
    —discuss
  19. Decryp Code U534 P1030680
    1 pointsby 33 minutes ago
    2comments
  20. A poem for the state of development in 2026
    1 pointsby 38 minutes ago
    —discuss
  21. Misleading AI-Generated Summaries Can Distort Human Memory (georgetown.edu)
    1 pointsby 41 minutes ago
    —discuss
  22. Wreckfall: Space Invaders but they crash to earth (abagames.itch.io)
    2 pointsby 43 minutes ago
    —discuss
  23. Fable Decides, Opus and Sonnet Do the Work: How I Route Claude Code Subagents (practicalsystems.io)
    1 pointsby 49 minutes ago
    2comments
  24. The Death of Educational Content on YouTube [video] (youtube.com)
    3 pointsby 58 minutes ago
    1comments
  25. How Not to Build a Shading Language – BCON26 [video] (youtube.com)
    1 pointsby 1 hour ago
    —discuss
  26. Show HN: Problee – play-money prediction markets (midterms, AI benchmarks, more) (problee.com)
    2 pointsby 1 hour ago
    1comments
  27. OpenAI axes next model citing safety issues (ft.com)
    4 pointsby 1 hour ago
    3comments
  28. Former PLA Officers Eavesdrop on South Korean, U.S. Military Bases (chosun.com)
    1 pointsby 1 hour ago
    —discuss
  29. Show HN: Jev Decision Layer: Save Frontier Tokens on Closed Decisions (github.com/qualixar)
    3 pointsby 1 hour ago
    —discuss
  30. OpenAI models may get more reasoning budget through the API than through Codex (twitter.com/tokengremlin)
    3 pointsby 1 hour ago
    —discuss

What 1,350 Runs Taught Us About Prompt Guardrails

1 pointsby 14m agohumanbound.ai
Open original View on HN
0 comments
A quiet thread, for now.Start the conversation on HN ↗