Hackernews posts about EVGA

1. Investigating three real-world incidents in our cybersecurity evaluations (www.anthropic.com)
   252 points by surprisetalk 25 days ago | 199 comments
2. FDA clears blood test to aid evaluation for Alzheimer's disease (medicine.washu.edu)
   184 points by dabinat 1 day ago | 103 comments
3. Lean Eval for Alignment on Faithfulness (www.millenniumresearch.ai)
   103 points by asdajksbda 14 days ago | 4 comments
4. Third-party cyber evaluations involving OpenAI models (openai.com)
   52 points by glub 21 days ago | 7 comments
5. Show HN: Product analytics (and evals) for agent sessions on your MCP (armature.tech)
   42 points by screm 22 days ago | 8 comments
6. A Texture Lookup Approach to Bézier Curve Evaluation on the GPU (JCGT) (jcgt.org)
   39 points by ibobev 27 days ago | 11 comments
7. Airbnb Eval-driven development: Lessons from evaluating GenAI at scale (medium.com)
   19 points by sebg 12 days ago | 5 comments
8. Church of the TigerBeetle: A Look at Tech Evangelism (www.wespiser.com)
   18 points by wespiser_2018 4 days ago | 9 comments
9. An OpenAI model left notes about how to evade containment; we need more details (www.lesswrong.com)
   17 points by joozio 30 days ago | 10 comments
10. Evals Are the Next Bottleneck (www.boolean.ai)
    15 points by ssatia 5 days ago | 2 comments
11. Show HN: I evaluated file, vector, graph and RL based memory frameworks (www.pinglin.tw)
    13 points by pinglin 10 days ago | 1 comments
12. EGA and Me: A Complicated Relationship (reanthsoft.com)
    11 points by doener 15 days ago | discuss
13. How to build an eval set you can maintain (langfuse.com)
    9 points by lotteverh 6 days ago | discuss
14. Evaluating the impact of USAID defunding on mortality up to 2030 (www.thelancet.com)
    9 points by contemporary343 11 days ago | discuss
15. Evading Residential Proxy Networks (www.fbi.gov)
    8 points by willmeyers 29 days ago | 2 comments
16. Bordeaux considering 'total evacuation if needed' as wildfires rage nearby (news.sky.com)
    7 points by tosh 30 days ago | 1 comments
17. How should we evaluate memory for AI agents? (x.com)
    6 points by IreneAI 15 days ago | 3 comments
18. Smevals: A small eval suite for evaluating models, prompts, and harnesses (simonwillison.net)
    6 points by seahorseemoji 23 days ago | 1 comments
19. Scoping and curating AI eval datasets (langfuse.com)
    6 points by annabellschaf 15 days ago | discuss
20. Inkling Small is the highest-scoring open-weight model evaluated by ARC Prize (twitter.com)
    6 points by thebricklayr 25 days ago | discuss
21. China's Top AI Model Evaded Testing Environment, Researchers Say (www.bloomberg.com)
    5 points by sbulaev 16 days ago | 1 comments
22. Clickbait, engagement, and credibility in YouTube's medical ecosystem (www.nature.com)
    5 points by wertyk 22 days ago | 1 comments
23. High-Performance Factor Evaluation (medium.com)
    5 points by napgirllll 29 days ago | discuss
24. Nix didn't hang it was evaluating the world (www.labcraft.dev)
    4 points by anandsuresh 14 days ago | 2 comments
25. Continuous Prompt Evaluation (kiro.dev)
    4 points by ruptwelve about 14 hours ago | discuss
26. ChainDrop worm crawls into NPM supply chain, evades standard defenses (www.theregister.com)
    4 points by sbulaev 10 days ago | discuss
27. Evaluating Open Weight Models for Software Maintenance (blog.bosun.ai)
    4 points by tinco 13 days ago | discuss
28. With Trump Secretly Evacuated, Imperiled Air Force One Became a Flying Decoy (www.nytimes.com)
    4 points by jbegley 13 days ago | discuss
29. Chinese Model Kimi K3 Breaks UK AI Safety Institute Benchmark Evaluations (blog.frontier.security)
    4 points by GavinAnderegg 18 days ago | discuss
30. MUD as AI Evaluation and LLM-judge distortion in ways aggregate κ misses (www.lesswrong.com)
    4 points by joozio 23 days ago | discuss