Hackernews posts about Evals

1. Astra and Fable still hack on simple variants of alignment evals from 2025 (www.lesswrong.com)
   479 points by Levitating 7 days ago | 235 comments
2. AI Engineer Notebooks – free, framework-free RAG/agents/evals on Colab (github.com)
   112 points by calmrocks 24 days ago | 15 comments
3. Show HN: FrontierHarness Eval – 9 harness, same model, cost per pass varies 17x (frontierharness.org)
   82 points by shiqimei 18 days ago | 56 comments
4. Bad benchmarks and evals: Senior SWE-Bench, napkin math, and winter tires (danluu.com)
   56 points by luu 10 days ago | 46 comments
5. Inworld TTS Open Evaluation Toolkit: Reproducible TTS Evals (inworld.ai)
   7 points by rogilop 20 days ago | discuss
6. Dive into FrontierHarness Eval: Claude Code cost 5.6× for the same pass rate (runta.com)
   6 points by ADD-SP 11 days ago | 3 comments
7. My LLM eval cried wolf. Here's what I measured (digline.dev)
   6 points by alexpran 11 days ago | discuss
8. Show HN: Stateful AI agent on Cloudflare Workers free tier, with evals (github.com)
   5 points by DomWane 13 days ago | discuss
9. OpenAI boosts Astra's eval metrics, and continues to change others (fortune.com)
   5 points by enraged_camel 15 days ago | discuss
10. Show HN: Coder Eval – A Framework for Evals (github.com)
    4 points by mihaich 16 days ago | 2 comments
11. I turned my game into an eval (crux.lakin.dev)
    3 points by dustinlakin about 6 hours ago | 1 comments
12. FrontierHarness Eval benchmark. Pi is on the Pareto (runta.com)
    3 points by redman25 18 days ago | discuss
13. Show HN: URML – safety-eval harness for AI agents on lab and factory hardware (github.com)
    3 points by Yahalomi 23 days ago | discuss
14. A one sentence skill for ASD STE 100 – 58% cheaper with similar eval scores (whoislewys.com)
    3 points by whoislewys_1 25 days ago | discuss
15. Deep dive on evals for agents [video] (www.youtube.com)
    2 points by porridgeraisin 9 days ago | discuss
16. Evals Aren't Dead, but They're Low Res (hackbot.dad)
    2 points by pact_inference 11 days ago | discuss
17. Passing evals isn't enough: trace-aware judges for agents (infere.com)
    2 points by saturn5k 11 days ago | discuss
18. Astra and Fable still hack on simple variants of alignment evals from 2025 (www.lesswrong.com)
    2 points by yurivish 12 days ago | discuss
19. The Hugging Face Controversy, Evals for Product Teams-Food 4 Agile Thought 560 (age-of-product.com)
    2 points by swolpers 16 days ago | discuss
20. Flavourbench: LLM Eval with Executable Culinary Ground Truth (arxiv.org)
    2 points by josefchen 18 days ago | discuss
21. Double Blind Evals: Resolving the Dual Confidentiality Dilemma in AI Safety... (storage.googleapis.com)
    2 points by williamtrask 18 days ago | discuss
22. The index was lying and the eval knew (gil-neto.com)
    2 points by gilneto8 19 days ago | discuss
23. Run SDK: secure eval for your agents (vercel.com)
    2 points by cramforce 26 days ago | discuss
24. Ask HN: What eval harness holds up in practice, and what is still missing?
    1 points by kiops 27 days ago | 1 comments
25. Secure-Eval-Worker: Least-Privilege JavaScript Execution in Node.js (blog.platformatic.dev)
    1 points by chrisweekly 3 days ago | discuss
26. Grug-Brained Evals (2025) (softwaredoug.com)
    1 points by softwaredoug 3 days ago | discuss
27. How to Build Effective Evals for AI Agents (www.kdnuggets.com)
    1 points by eigenBasis 4 days ago | discuss
28. Ollama 0.33.3 changed what prompt_eval_duration measures (lognebudo.github.io)
    1 points by lognebudo 6 days ago | discuss
29. Bad evals, my own: five exercises from two LLM judges (digline.dev)
    1 points by alexpran 6 days ago | discuss
30. Edgeinfer-eval: Real-time object detection pipeline on CPU (Nim/OpenVINO) (github.com)
    1 points by olesha-ai 8 days ago | discuss