Hackernews posts about EVGA

1. Meta and TikTok let harmful content rise to drove engagement, say whistleblowers (www.bbc.com)
   331 points by 1vuio0pswjnm7 26 days ago | 194 comments
2. Oregon school cell phone ban: 'Engaged students, joyful teachers' (portlandtribune.com)
   278 points by nxobject 23 days ago | 234 comments
3. EsoLang-Bench: Evaluating Genuine Reasoning in LLMs via Esoteric Languages (esolang-bench.vercel.app)
   99 points by matt_d 24 days ago | 59 comments
4. Hawaii's worst flooding in 20 years threatens dam, prompts evacuations (www.nbcnews.com)
   79 points by geox 22 days ago | 45 comments
5. PGLite Evangelism (substack.com)
   76 points by surprisetalk 4 days ago | 26 comments
6. Evacuation of U.S. troops from Mideast base sends community groups scrambling (www.npr.org)
   45 points by ceejayoz 8 days ago | 18 comments
7. US forces locate and evacuate downed airman in Iran (www.foxnews.com)
   25 points by longislandguido 8 days ago | 84 comments
8. Show HN: Mtproto.zig – High-performance Telegram proxy with DPI evasion (github.com)
   24 points by slp3r 9 days ago | 15 comments
9. High income improves evaluation of life but not emotional well-being (www.pnas.org)
   16 points by RickJWagner 27 days ago | 2 comments
10. AI Disrupts Talent Evaluation Before It Disrupts Talent (substack.com)
    8 points by cactaceae 22 days ago | 2 comments
11. A Digital Compute-in-Memory Architecture for NFA Evaluation (dl.acm.org)
    8 points by blakepelton 6 days ago | 1 comments
12. Comprehensive Benchmark for Evaluating AI on Graphic Design Tasks (arxiv.org)
    8 points by pritopian 5 days ago | discuss
13. Meta and TikTok let harmful content rise after evidence outrage drove engagement (www.bbc.com)
    8 points by vinni2 27 days ago | discuss
14. Show HN: Pipevals – a visual pipeline builder for evaluation-driven AI (github.com)
    6 points by tilt 23 days ago | 2 comments
15. Apple's Spotlight Search Results Come with Engagement Metrics. No One Knew (www.buchodi.com)
    6 points by lmbbuchodi 9 days ago | discuss
16. Fossier: A slop evaluator for GitHub PRs to prevent spams (github.com)
    6 points by SchwKatze 13 days ago | discuss
17. Astronaut's Condition That Led to Space Station Evacuation Remains a Mystery (www.nytimes.com)
    5 points by Brajeshwar 15 days ago | 2 comments
18. Show HN: LLMadness – March Madness Model Evals (llmadness.com)
    5 points by rjkeck2 25 days ago | 2 comments
19. How Iranians are evading internet blocks to contact family abroad (www.bbc.com)
    5 points by colinprince 28 days ago | 1 comments
20. Israel Mounts Lavish Campaign to Win Back Evangelicals (washingtonspectator.org)
    5 points by throw310822 about 15 hours ago | discuss
21. Composer 2 scores highest in React Native evals with 96% (rn-evals.vercel.app)
    5 points by thymikee 19 days ago | discuss
22. SysMoBench: Evaluating AI on Formally Modeling Complex Real-World Systems (muratbuffalo.blogspot.com)
    5 points by matt_d 19 days ago | discuss
23. Auto-harness: Self improving agentic systems with auto-evals (open-sourced) (twitter.com)
    4 points by gauri1902 9 days ago | 3 comments
24. Adding evals to a satelite image agent with a Claude Skill (medium.com)
    4 points by jangletown 19 days ago | 2 comments
25. Show HN: EvalsHub: Your AI is failing in production and you don't know it (www.evalshub.ai)
    4 points by neilsharma425 23 days ago | 1 comments
26. What Digital Isolation and Censorship Evasion Look Like in Wartime Iran (www.techpolicy.press)
    4 points by mooreds 7 days ago | discuss
27. How to Evaluate Claude Skill Output Quality for Prompt-to-SQL Scenarios (dekart.xyz)
    4 points by delfrrr 9 days ago | discuss
28. Show HN: Pre-training, fine-tuning, and evals platform (www.oumi.ai)
    4 points by oli_kitty 9 days ago | discuss
29. Astronaut's Condition That Led to Space Station Evacuation Remains a Mystery (www.nytimes.com)
    4 points by Tomte 13 days ago | discuss
30. Show HN: Evals Skills (langwatch.ai)
    4 points by jangletown 20 days ago | discuss