Hackernews posts about Evals

1. Show HN: Agent-evals – Claude skill to build your own evals (github.com)
   9 points by sauercrowd 2 days ago | 1 comments
2. Zork-bench: An LLM reasoning eval based on text adventure games (www.lowimpactfruit.com)
   5 points by mnky9800n 13 days ago | discuss
3. Gbrain-Evals (github.com)
   4 points by mjtk 13 days ago | 1 comments
4. AI evals are becoming the new compute bottleneck (huggingface.co)
   4 points by gmays 2 days ago | discuss
5. Product Evals in Three Simple Steps (eugeneyan.com)
   3 points by eigenBasis 9 days ago | discuss
6. I built a multi-turn clinical safety eval framework for LLMs (medium.com)
   3 points by deepikaa_s 19 days ago | discuss
7. Show HN: Legal Action Boundary Eval for agentic legal workflows (github.com)
   2 points by kankouadio_vx 14 days ago | 2 comments
8. Cyborg Evals (www.lesswrong.com)
   2 points by frmsaul 6 days ago | 1 comments
9. Dolibarr 23.0.0: PHP eval() whitelist bypass → RCE via two bugs (CVE-2026-22666) (jivasecurity.com)
   2 points by jiva 23 days ago | 1 comments
10. Show HN: AHD – an open-source linter and eval framework for AI-generated UI (ahd.adastra.computer)
    2 points by HereticLocke 1 day ago | discuss
11. Evals Skills for AI Agents (github.com)
    2 points by paulaq 3 days ago | discuss
12. Zork-bench: An LLM reasoning eval based on text adventure games (www.lowimpactfruit.com)
    2 points by nicholasjbs 9 days ago | discuss
13. Show HN: Phinite – The OS layer (eval, observe, govern, A2A native) (www.phinite.ai)
    2 points by PhiniteAI 11 days ago | discuss
14. Show HN: Claude Code skills for building LLM evals (github.com)
    2 points by paulaq 13 days ago | discuss
15. Show HN: FieldOps-Bench an open eval for physical-world AI agents (www.camerasearch.ai)
    1 points by Aeroi 15 days ago | 1 comments
16. LLM-eval-kit: Distributed LLM evaluation framework (v0.3.0) (github.com)
    1 points by benmeryem_ai 5 days ago | discuss
17. Task-Specific LLM Evals That Do and Don't Work (eugeneyan.com)
    1 points by eigenBasis 6 days ago | discuss
18. AI evals are becoming the new compute bottleneck (huggingface.co)
    1 points by ibobev 6 days ago | discuss
19. Build AI evals from real failures (latitude.so)
    1 points by paulaq 17 days ago | discuss
20. Code → Eval → HLD → LLD → Code (p10q.com)
    1 points by tmsh 18 days ago | discuss
21. Bootstrapping AI Evals from Context (Why 'Just Asking Claude' Fails) (scorable.ai)
    1 points by Arimbr 20 days ago | discuss
22. Coding evals are broken. CI is green while AI code quality goes unmeasured (www.stet.sh)
    1 points by bisonbear 21 days ago | discuss
23. Show HN: 2500 vision benchmarks / evals for Vision Language Models (github.com)
    1 points by zakariaelhjouji 28 days ago | discuss
24. Show HN: Nyx – multi-turn, adaptive, offensive testing harness for AI agents (fabraix.com)
    20 points by zachdotai 17 days ago | 8 comments
25. Show HN: Spec27 – Spec-driven validation for AI agents (www.spec27.ai)
    13 points by njyx 7 days ago | 9 comments
26. Show HN: Netlify for Agents (netlify.ai)
    13 points by bobfunk 14 days ago | 4 comments
27. Show HN: I forced Claude to play Tetris in Emacs (imgur.com)
    13 points by iLemming 26 days ago | 3 comments
28. I built a hiring platform that watches engineers work in a real CAD tool
    7 points by mind_uncapped 10 days ago | discuss
29. Show HN: I built a way to see if your SDK is AI-friendly
    4 points by nguyenhu 9 days ago | discuss
30. Show HN: API Ingest – Agentic Search (Inter) API Docs (github.com)
    3 points by mohidbutt 14 days ago | 2 comments