Hackernews posts about EVGA

1. OpenAI and Hugging Face address security incident during model evaluation (openai.com)
   1624 points by mfiguiere 5 days ago | 1155 comments
2. Evidence of inconsistencies in evaluation process and selection of winners (www.kaggle.com)
   474 points by twerkmeister 9 days ago | 298 comments
3. Odin, Wikipedia and engagement farming (katamari64.se)
   262 points by stock_toaster 22 days ago | 407 comments
4. Separating signal from noise in coding evaluations (openai.com)
   239 points by sk4rekr0w 18 days ago | 97 comments
5. Can a MUD evaluate LLMs? A $99 proof of concept (cruciblebench.ai)
   109 points by Davisb135 4 days ago | 78 comments
6. Evan's Jujutsu Tutorial (evmar.github.io)
   78 points by joecobb 30 days ago | 7 comments
7. Ask HN: Why are so many "AI evangelists" posting such insufferable content?
   70 points by seattle_spring 24 days ago | 40 comments
8. Tech Workers Face Evaporating Financial Security as AI Transforms Industry (www.adn.com)
   46 points by nlpnerd 6 days ago | 35 comments
9. Midtown Manhattan blocks evacuated after beams buckling at construction site (abcnews.com)
   46 points by danso 19 days ago | 32 comments
10. Evaluation order and nontermination in query languages (www.rntz.net)
    44 points by luu 24 days ago | 6 comments
11. An independent evaluation of TabFM, Google's tabular foundation model (yashrajpandey.com)
    25 points by yashrajpandey 20 days ago | 1 comments
12. Vessel An EGA adventure about whether machines can grieve (claude.ai)
    22 points by schwarzarno 19 days ago | 8 comments
13. Furtex: Post-exploitation, rootkit and evasion research toolkit for Linux (github.com)
    18 points by matheuzsec_ 4 days ago | 2 comments
14. OpenAI announces models hacked Hugging Face during an eval (runtimewire.com)
    15 points by ryanmerket 5 days ago | 1 comments
15. Aircraft crashes into Beijing's tallest skyscraper, triggering evacuations (www.dailymail.com)
    12 points by Bender 30 days ago | 5 comments
16. From Evaluation to Guardrails: What We Brought to ACM FAccT 2026 (blog.mozilla.ai)
    12 points by royapakzad 3 days ago | discuss
17. Why Most Evals Are Bad (www.boolean.ai)
    11 points by sks 1 day ago | discuss
18. Summary of METR's predeployment evaluation of GPT-5.6 Sol (metr.org)
    10 points by pongogogo 30 days ago | 6 comments
19. Online vs. Offline AI Evals: When to Use Each (www.inngest.com)
    10 points by aldersondev 12 days ago | 3 comments
20. What founders should evaluate before launching an AI-built app (geekyants.com)
    8 points by Krishnaswaroop 17 days ago | 3 comments
21. X509-limbo: testvectors and tooling for evaluating X.509 path validation (x509-limbo.com)
    8 points by sscaryterry 19 days ago | 1 comments
22. Northwestern's Phantom Twist spins at 1,500 RPM to evade human vision (runtimewire.com)
    7 points by ryanmerket 6 days ago | discuss
23. "It's Hard to Eval" Is a Product Smell (hamel.dev)
    7 points by call-me-al 26 days ago | discuss
24. It's Hard to Eval Is a Product Smell (hamel.dev)
    6 points by _pdp_ 22 days ago | 1 comments
25. As the cost of aging soars, families' wealth is evaporating (www.washingtonpost.com)
    6 points by elo2000 3 days ago | discuss
26. The Prompt-Wait-Evaluate Loop: How AI Kills Flow Without You Noticing (www.sandordargo.com)
    6 points by jandeboevrie 11 days ago | discuss
27. Evaluation of a pentapropellant upper stage (1970) [pdf] (ntrs.nasa.gov)
    5 points by Eridanus2 1 day ago | 1 comments
28. Know thine enemy: A critical engagement with AI-assisted software development (medium.com)
    5 points by linggen 13 days ago | 1 comments
29. A social media engine that learns from every post's engagement (postlore.com)
    5 points by ggap 13 days ago | 1 comments
30. A little experiment in evading AI detection (thegustafson.com)
    5 points by usernotfoundrn 8 days ago | discuss