Hackernews posts about BenQ

1. Exploiting the most prominent AI agent benchmarks (rdi.berkeley.edu)
   588 points by Anon84 19 days ago | 143 comments
2. SWE-bench Verified no longer measures frontier coding capabilities (openai.com)
   340 points by kmdupree 4 days ago | 180 comments
3. Up to 8M Bees Are Living in an Underground Network Beneath This Cemetery (www.discovermagazine.com)
   183 points by janandonly 13 days ago | 31 comments
4. Lambda Calculus Benchmark for AI (victortaelin.github.io)
   142 points by marvinborner 5 days ago | 43 comments
5. Monumental ship burial beneath ancient Norwegian mound predates the Viking Age (phys.org)
   106 points by pseudolus 13 days ago | 27 comments
6. N-Day-Bench – Can LLMs find real vulnerabilities in real codebases? (ndaybench.winfunc.com)
   91 points by mufeedvh 17 days ago | 29 comments
7. I benchmarked Claude Code's caveman plugin against "be brief." (www.maxtaylor.me)
   88 points by max-t-dev about 19 hours ago | 64 comments
8. High-Level Rust: Getting 80% of the Benefits with 20% of the Pain (hamy.xyz)
   81 points by maxloh 19 days ago | 117 comments
9. MemPalace, the highest-scoring AI memory system ever benchmarked (github.com)
   67 points by rochoa 23 days ago | 17 comments
10. A cache-friendly IPv6 LPM with AVX-512 (linearized B+-tree, real BGP benchmarks) (github.com)
    64 points by debugga 11 days ago | 23 comments
11. Show HN: A new benchmark for testing LLMs for deterministic outputs (interfaze.ai)
    55 points by khurdula 1 day ago | 23 comments
12. Ben Lerner's Big Feelings (www.vulture.com)
    43 points by prismatic 14 days ago | 22 comments
13. The underrated benefits of always having oatmeal at lunch (hazn.com)
    39 points by surprisetalk 28 days ago | 60 comments
14. Idiomatic Lisp and the Nbody Benchmark (www.stylewarning.com)
    36 points by signa11 27 days ago | discuss
15. CDC director delays report showing Covid vaccine benefits (www.theguardian.com)
    26 points by iamflimflam1 18 days ago | 2 comments
16. Contra Benn Jordan, data center (and all) sub-audible infrasound issues are fake (blog.andymasley.com)
    23 points by logicprog 11 days ago | 15 comments
17. Show HN: Mdarena – Benchmark your Claude.md against your own PRs (github.com)
    22 points by hudsongr 25 days ago | 4 comments
18. CDC delays publishing report showing Covid vaccine benefits (www.washingtonpost.com)
    22 points by ceejayoz 21 days ago | 2 comments
19. The highest-scoring AI memory system ever benchmarked (github.com)
    21 points by latchkey 24 days ago | 3 comments
20. Xiaomi releases MiMo-v2.5 Family weights with strong coding and agent benchmarks (firethering.com)
    20 points by steveharing1 2 days ago | 7 comments
21. CDC study shows Covid shot benefits; Trump official blocks release (arstechnica.com)
    20 points by ColinWright 21 days ago | 4 comments
22. Precision over perception: Why architecture matters in benchmarking (www.redhat.com)
    19 points by salkahfi 17 days ago | discuss
23. We're running out of benchmarks to upper bound AI capabilities (www.lesswrong.com)
    15 points by gmays 20 days ago | 10 comments
24. Index providers shouldn't bend the rules for Elon Musk (economist.com)
    12 points by andsoitis 29 days ago | 2 comments
25. The Importance of Benchmarks (www.aha.io)
    11 points by FigurativeVoid 17 days ago | 1 comments
26. Show HN: Codex context bloat? 87% avg reduction on SWE-bench Verified traces (www.npmjs.com)
    10 points by george_ciobanu 6 days ago | 2 comments
27. Show HN: ParseBench – Document parsing benchmark for AI agents (www.parsebench.ai)
    9 points by pierre 17 days ago | 5 comments
28. Show HN: ACE – A dynamic benchmark measuring the cost to break AI agents (fabraix.com)
    9 points by zachdotai 25 days ago | 3 comments
29. Show HN: I benchmarked Gemma 4 E2B – the 2B model beat the 12B on multi-turn (aiexplr.com)
    8 points by mailharishin 17 days ago | 1 comments
30. Poll: Majority of voters say risks of AI outweigh the benefits (www.nbcnews.com)
    8 points by cdrnsf 20 days ago | 1 comments