Show HN: AI Roundtable – Let 200 models debate your question(opper.ai)

55 points by felix089 7 months ago | 47 comments

“Car Wash” test with 53 models(opper.ai)

340 points by felix089 8 months ago | 403 comments

Opper blog post testing 53 AI models on the 'car wash 50 meters away, walk or drive?' logic question, with repeated runs and a human baseline.

Core copyright violation moves ahead in The Intercept's lawsuit against OpenAI(niemanlab.org)

286 points by giuliomagnifico 1 year ago | 305 comments

Advertise in ChatGPT(ads.openai.com)

1012 points by montecarl 3 months ago | 774 comments

OpenAI's landing page for advertisers to buy relevant ads that appear inside ChatGPT conversations.

Capsem – a Rust hypervisor sandboxing AI agents in air-gapped Linux VMs(capsem.org)

5 points by madars 11 days ago | 2 comments

Landing page for Capsem, a Rust-powered hypervisor that sandboxes each AI coding agent in its own air-gapped Linux VM for visibility and control.

OpenAI: Start using ChatGPT instantly(openai.com)

92 points by Josely 2 years ago | 116 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.

Show HN: Jev Plays Pokémon Red(jev-pokemon.vercel.app)

258 points by pancomplex 1 month ago | 109 comments

Landing page for Jev Plays Pokémon Red, a live YouTube stream of the Jev AI decision model playing Pokémon Red, with links to open-source code.

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

62 points by thefourthchime 27 days ago | 38 comments

PacBench, a benchmark site comparing how well AI model and harness combinations recreate a Pac-Man game in a single HTML page from one prompt.

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.

DeepSeek V4.1 Flash 1017 (Max)(artificialanalysis.ai)

159 points by theanonymousone 7 days ago | 58 comments

Artificial Analysis model page benchmarking DeepSeek V4.1 Flash 1017 (Max) on intelligence, speed, and price.

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.