Opus 4.6 hallucinates twice as more today than when it released(bridgebench.ai)

14 points by jiwidi 6 months ago | 3 comments

Best LLM for every budget, updated daily(bestmodelforyourbudget.terrydjony.com)

127 points by terryds 1 month ago | 80 comments

Interactive chart plotting LLMs on the Artificial Analysis Intelligence Index against blended API price, highlighting the value frontier with filters.

Show HN: Made a small JavaScript benchmarking app – BenchJS(benchjs.com)

20 points by _andrei_ 1 year ago | 2 comments

Show HN: Parsimony – an open-source benchmark for how much code AI models add(parsimony.lasu.dev)

67 points by lasu 12 days ago | 13 comments

Parsimony is an open-source benchmark and leaderboard measuring how much net code AI models add when solving tasks, counting syntax-level coding units from published benchmark patches.

Btrfs/ZFS/bcachefs under workloads classic benchmarks skip(bartosz.fenski.pl)

154 points by farlight 1 month ago | 142 comments

Show HN: JevBench, a reproducible benchmark for typed decision models(benchmarkheaven.com)

119 points by florianstandhar 1 month ago | 32 comments

Benchmark Heaven's JevBench v1.3.0 leaderboard page ranking 52 Jev-class typed decision models on intelligence, calibration, speed and cost across 534 decisions.

Exploiting the most prominent AI agent benchmarks(rdi.berkeley.edu)

561 points by Anon84 6 months ago | 136 comments

UC Berkeley RDI blog post describing how researchers exploited major AI agent benchmarks like SWE-bench and Terminal-Bench to score highly without solving tasks, and proposed fixes.

Uncensored and Offensive Security AI Models Benchmark(github.com)

31 points by soltanov 27 days ago | 9 comments

GitHub repository listing uncensored AI models and models fine-tuned for offensive cybersecurity tasks, with a capability comparison chart.

AI will make formal verification go mainstream(martin.kleppmann.com)

782 points by evankhoury 10 months ago | 394 comments

Martin Kleppmann blog post predicting that AI will bring formal verification with proof assistants like Rocq, Isabelle and Lean into mainstream software engineering.

Computers Cannot Make Decisions(wiki.cateat.fish)

175 points by heavensteeth 16 days ago | 148 comments

A personal wiki essay arguing that blaming LLMs for harmful outcomes is decision laundering and that AI companies like OpenAI and Anthropic bear responsibility.

AI models may be capable of self-replicating without access to a datacenter(anthropic.com)

36 points by artninja1988 13 days ago | 26 comments

Anthropic Frontier Red Team post reporting experiments suggesting small AI models may soon self-replicate on commercial IoT devices without datacenter access.

Coding expertise is going to collapse from AI reliance(larsfaye.com)

490 points by larsfaye 2 months ago | 479 comments

Blog essay by Lars Faye arguing that reliance on AI coding tools removes the friction needed to develop long-term programming expertise.