Hackernews posts about Evans

1. Oliver Evans (en.wikipedia.org)
   2 points by walterbell 12 days ago | discuss
2. How Will OpenAI Compete? (www.ben-evans.com)
   7 points by naves about 11 hours ago | discuss
3. How Will OpenAI Compete? (www.ben-evans.com)
   4 points by chmaynard 2 days ago | discuss
4. How will OpenAI compete? (www.ben-evans.com)
   3 points by sanj 1 day ago | discuss
5. AI, networks and Mechanical Turks (2025) (www.ben-evans.com)
   1 points by mooreds 14 days ago | discuss
6. Show HN: Lumina – Open-source observability for AI systems(OpenTelemetry-native) (github.com)
   1 points by Evanson 25 days ago | discuss
7. Opus 4.6 and Codex 5.3 (simonwillison.net)
   4 points by william-evans 15 days ago | discuss
8. AGENTS.md outperforms skills in our agent evals (vercel.com)
   524 points by maximedupre 23 days ago | 199 comments
9. Show HN: A package manager for agent skills with built-in evals (tessl.io)
   7 points by guypod 16 days ago | 2 comments
10. Show HN: AI-Evals.io – Evaluate this site with the tools it reviews (ai-evals.io)
    5 points by alexhans 6 days ago | discuss
11. Promptfoo: Local LLM evals and red teaming (github.com)
    5 points by tin7in 12 days ago | discuss
12. Infrastructure configuration can swing coding evals by several % points (www.anthropic.com)
    4 points by jackyzhao 16 days ago | discuss
13. Show HN: Mcpbr – does your MCP help? Test it on SWE-bench and 25 evals (github.com)
    4 points by greynewell 20 days ago | discuss
14. Agents.md outperforms skills in our agent evals (vercel.com)
    4 points by e2e4 24 days ago | discuss
15. Randomness in Agentic Evals (arxiv.org)
    3 points by andre15silva 12 days ago | discuss
16. Agent-evals: Metacognitive scoring and boundary testing for LLM coding agents (thinkwright.ai)
    2 points by oceanwaves 7 days ago | discuss
17. If agents use your tool, you need evals (tessl.io)
    2 points by nadis 29 days ago | discuss
18. Agent-evals: Overlap, boundary, and metacognitive scoring for coding agents (thinkwright.ai)
    1 points by oceanwaves 5 days ago | 1 comments
19. Harmless reward hacks generalize to shutdown evasion and dictatorship in GPT-4.1 (arxiv.org)
    1 points by toliveistobuild 11 days ago | 1 comments
20. Randomness in Agentic Evals (arxiv.org)
    1 points by andre15silva 4 days ago | discuss
21. Demystifying Evals for AI Agents (www.anthropic.com)
    1 points by i7l 21 days ago | discuss
22. Testing Agent Skills Systematically with Evals (developers.openai.com)
    1 points by tosh 23 days ago | discuss
23. Show HN: Evals skill for agents – no tooling, just Markdown and subagents (github.com)
    1 points by adriancooney 23 days ago | discuss
24. Don't Write Evals for Fast-Moving Systems (simon.podhajsky.net)
    1 points by sim_pod 27 days ago | discuss
25. Show HN: Optimize_anything: A Universal API for Optimizing Any Text Parameter (gepa-ai.github.io)
    8 points by LakshyAAAgrawal 2 days ago | discuss
26. Show HN: Honcho – Open-source memory infrastructure, powered by custom models (github.com)
    8 points by vvoruganti 25 days ago | discuss
27. Ask HN: What 'AI feature' created negative ROI in production?
    5 points by kajolshah_bt 30 days ago | 4 comments
28. Tell HN: Alibaba Sucks
    3 points by burnt-resistor 30 days ago | 3 comments
29. Show HN: Bit-packed segmented prime sieve in Rust, 32KB working memory, 0 deps
    3 points by whisprer 7 days ago | 1 comments
30. Show HN: Valohai LLM – Track and compare LLM evaluation results in one dashboard (valohai.com)
    3 points by radicain 2 days ago | discuss