Hackernews posts about Ben

1. 01
   

   new90% of US working hours are spent on tasks not covered well by AI benchmarkswww.mercor.com

   ▲ 612speckx2d💬 563savesaved
2. 02
   

   newBrood War Benchbw.swerdlow.dev

   ▲ 346benswerd29d💬 156savesaved
3. 03
   

   newBtrfs/ZFS/bcachefs under workloads classic benchmarks skipbartosz.fenski.pl

   ▲ 179farlight29d💬 190savesaved
4. 04
   

   newLLM Ass Benchwww.assbench.com

   ▲ 170fragmede25d💬 46savesaved
5. 05
   

   newShow HN: JevBench, a reproducible benchmark for typed decision modelsbenchmarkheaven.com

   ▲ 154florianstandhar26d💬 39savesaved
6. 06
   

   newBenchmark in Millisecondsmatklad.github.io

   ▲ 148surprisetalk13d💬 53savesaved
7. 07
   

   newThe engineering that allows articulated buses to bendwww.theautopian.com

   ▲ 135CharlesW3d💬 62savesaved
8. 08
   

   newAn algorithmic failure beneath the secret ballotblog.citp.princeton.edu

   ▲ 110leecoursey15d💬 101savesaved
9. 09
   

   newShow HN: Pac-Bench – How well can models one-shot a Pac-Man game?jonclegg.github.io

   ▲ 80thefourthchime19d💬 50savesaved
10. 10
    

    newTexas police department ordered to close for failing to provide public benefitwww.dallasnews.com

    ▲ 77Danhale9326d💬 34savesaved
11. 11
    

    newShow HN: Parsimony – an open-source benchmark for how much code AI models addparsimony.lasu.dev

    ▲ 77lasu4d💬 19savesaved
12. 12
    

    newAccept 'bad things' in return for benefits of AI, says Sam Altmanwww.theguardian.com

    ▲ 64samizdis13d💬 123savesaved
13. 13
    

    newScaling and benchmarking a critical message bus using a new indexing strategyblog.janestreet.com

    ▲ 52eatonphil10d💬 3savesaved
14. 14
    

    newBenchmarking Wild vs. Molddavidlattimore.github.io

    ▲ 47birdculture28d💬 1savesaved
15. 15
    

    newAltman: The world should accept some bad things happening for the benefits of AIwww.politico.com

    ▲ 42jamesgill13d💬 44savesaved
16. 16
    

    newEarth is tearing apart beneath the Pacific Northwestwww.sciencedaily.com

    ▲ 29emot22d💬 16savesaved
17. 17
    

    newShape-sensing sheet digitally tracks its own movement as it bends and twistsnews.mit.edu

    ▲ 28bookofjoe8ddiscusssavesaved
18. 18
    

    newBenchmarking retrieval for agents on messy real-world company knowledgewww.kapa.ai

    ▲ 27emil_sorensen16d💬 3savesaved
19. 19
    

    newShow HN: AI SRE Arena, an Open Benchmark for AI SRE Agents on Kubernetesgithub.com

    ▲ 24emrahsamdan10d💬 10savesaved
20. 20
    

    newDoGBench: The first user-facing docs generation benchmark. No model scores >50%dogbench.ai

    ▲ 19prithvi220616d💬 3savesaved
21. 21
    

    newThe dot and the Swarm: Benefitting from the bitter lessonwww.oneusefulthing.org

    ▲ 14bluepeter16d💬 5savesaved
22. 22
    

    newBender: AI's 'Existential' Risk Is 'Fake' [video]www.youtube.com

    ▲ 12Moru11d💬 15savesaved
23. 23
    

    newYoshua Bengio: 'If you prioritize safety, leave frontier AI companies'www.transformernews.ai

    ▲ 12thoughtpeddler9ddiscusssavesaved
24. 24
    

    newBen Affleck is an AI nerdtwitter.com

    ▲ 10ulrischa9d💬 3savesaved
25. 25
    

    newROCmFix and InferBench – AMD Local-LLM Setup and Vulkan vs. Hip Benchmarkinggithub.com

    ▲ 10Xanpavle28d💬 2savesaved
26. 26
    

    newTaste Benchwww.omneky.com

    ▲ 10hsenju23d💬 1savesaved
27. 27
    

    newAltman: `World should accept some bad things happening' for the benefits of AIwww.politico.com

    ▲ 8theanonymousone13d💬 14savesaved
28. 28
    

    newFrontierML: A challenging, end-to-end machine learning benchmarkwww.frontierml.org

    ▲ 8meetpateltech5d💬 1savesaved
29. 29
    

    newAI Coding Tools – Architecture diagrams, local models, and SWE-benchgithub.com

    ▲ 8mahmoudsajjadi10ddiscusssavesaved
30. 30
    

    newGrok Voice tops new benchmarkveris.ai

    ▲ 8jrm-veris13ddiscusssavesaved

· edit