Hackernews posts about Evals

1. Agents.md file isn't the problem. Your lack of Evals is (tessl.io)
   42 points by sjmaplesec 25 days ago | 17 comments
2. Ask HN: How are people doing AI evals these days?
   30 points by yelmahallawy 11 days ago | 43 comments
3. Show HN: LLMadness – March Madness Model Evals (llmadness.com)
   5 points by rjkeck2 2 days ago | 2 comments
4. Show HN: SOTA long memory eval with open source models (ensue.dev)
   5 points by austinbaggio 18 days ago | discuss
5. Show HN: EvalsHub: Your AI is failing in production and you don't know it (www.evalshub.ai)
   4 points by neilsharma425 about 22 hours ago | 1 comments
6. Show HN: LLM Council – Run multiple LLMs with critique and consensus eval (github.com)
   4 points by gauravvij137 24 days ago | discuss
7. Test Evals Are Not Enough (voratiq.com)
   3 points by languid-photic 10 days ago | 2 comments
8. Better practical evals for real-world LLM agents (www.colehoffer.ai)
   3 points by choffer 22 days ago | 1 comments
9. Show HN: FC-Eval – CLI to Benchmark Local or Cloud LLMs on Function Calling (github.com)
   3 points by gauravvij137 4 days ago | discuss
10. Show HN: Rhesis AI - Multimodal test cases for agentic evals
    3 points by nicolaib 5 days ago | discuss
11. Evaluating Claude's dbt Skills: Building an Eval from Scratch (rmoff.net)
    3 points by rmoff 8 days ago | discuss
12. Selectively reducing eval awareness and murder in Gemma 3 27B via steering (www.lesswrong.com)
    3 points by gmays 9 days ago | discuss
13. Eval awareness in Claude Opus 4.6's BrowseComp performance (www.anthropic.com)
    3 points by GaggiX 13 days ago | discuss
14. AoE 2 Build Order as an Eval for LLM's (wraitii.github.io)
    3 points by liamzebedee 28 days ago | discuss
15. Open-source LLM-as-judge eval suite with root cause analysis and failure mining (github.com)
    2 points by colinfly 8 days ago | 1 comments
16. LLM evals test outputs. Rarely whether the model understood first (github.com)
    2 points by noxion about 24 hours ago | discuss
17. We ran 600 agent evals – steering hooks hit 100% accuracy, prompts hit 82% (strandsagents.com)
    2 points by aspittel 3 days ago | discuss
18. Bonsai: Use It Where Eval() Would Be Reckless (danfry1.github.io)
    2 points by thunderbong 5 days ago | discuss
19. AST-filtered eval() is not a sandbox: Severity 10 CVE-2026-26030, and others (daridor.blog)
    2 points by beagle3 14 days ago | discuss
20. Eval awareness in Claude Opus 4.6's BrowseComp performance (www.anthropic.com)
    2 points by gcampbell 15 days ago | discuss
21. Ask HN: Do you write evals for your skills?
    1 points by dominotw about 5 hours ago | discuss
22. Quantifying infrastructure noise in agentic coding evals (www.anthropic.com)
    1 points by gmays 6 days ago | discuss
23. Show HN: Iris – first MCP-native eval and observability tool for AI agents (github.com)
    1 points by iparent 7 days ago | discuss
24. Show HN: An agent skill for eval-driven development of LLM-powered app (github.com)
    1 points by yol 9 days ago | discuss
25. Eval awareness in Claude Opus 4.6’s BrowseComp performance (www.anthropic.com)
    1 points by upmind 12 days ago | discuss
26. Show HN: Skill Eval – A framework for testing the quality of AI agent skills (blog.mgechev.com)
    1 points by mgechev 17 days ago | discuss
27. Evals Skills for Coding Agents (hamel.dev)
    1 points by call-me-al 17 days ago | discuss
28. Webgrid Eval: LLM vision + tool-use on Neuralink's cursor control task (github.com)
    1 points by ofou 24 days ago | discuss
29. Show HN: Context Gateway – Compress agent context before it hits the LLM (github.com)
    97 points by ivzak 8 days ago | 64 comments
30. Show HN: Optimize_anything: A Universal API for Optimizing Any Text Parameter (gepa-ai.github.io)
    8 points by LakshyAAAgrawal 30 days ago | discuss