A third of Perplexity's citations don't contain the number they're cited for(hausresearch.com)

120 points by jakobgreenfeld 1 month ago | 43 comments

We ran Anthropic’s interviews through structured LLM analysis(playbookatlas.com)

68 points by jp8585 10 months ago | 66 comments

GPT-5.6 vs. Claude Fable 5 for Physical AI, which performs best?(juliahub.com)

82 points by mbauman 2 months ago | 18 comments

The Parallel Search API(parallel.ai)

108 points by lukaslevert 11 months ago | 45 comments

A Summary of Ilya Sutskevers AI Reading List(tensorlabbet.com)

14 points by tarolangner 2 years ago | 1 comments

Three AI agents, two countries, and one uneven world wide web(royapakzad.substack.com)

35 points by effects 24 days ago | 1 comments

Substack post by researcher Roya Pakzad comparing how GPT, Claude, and Muse AI agents handle multilingual research, source access, human-in-the-loop, and observability.

Generative Models: What do they know? Do they know things? Let's find out(intrinsic-lora.github.io)

330 points by corysama 2 years ago | 106 comments

Project page for a research paper from TTIC and Adobe probing whether generative image models encode intrinsic scene properties like normals, depth, albedo and shading.

Some critical issues with the SWE-bench dataset(arxiv.org)

331 points by joshwa 1 year ago | 113 comments

arXiv paper introducing SWE-Bench+, an empirical analysis revealing data quality issues in the SWE-bench coding benchmark for LLMs, such as solution leakage and weak tests.

CEO fired developers to make room for AI. Developers create open source AI CEO(github.com)

852 points by GrumpySciGuy 2 months ago | 585 comments

GitHub repository for OpenExecutive, an open source AI virtual executive team built from 8 specialist Claude agents using FastAPI and Next.js.

Auto-research with codex: How I achieved a 232x Faster Kernel(sankalp.bearblog.dev)

424 points by tosh 2 months ago | 91 comments

Blog post on using OpenAI Codex for automated research to optimize a kernel 232x faster; the captured page shows a Cloudflare verification screen.

AI-Assisted Paper on Z-Library Cites a TorrentFreak Article That Doesn't Exist(torrentfreak.com)

80 points by TangerineDream 2 days ago | 37 comments

TorrentFreak article reporting that an AI-assisted peer-reviewed paper on Z-Library cites a nonexistent TorrentFreak article and other unfindable sources.

AI tutoring with Khanmigo in a two-year school experiment(edworkingpapers.com)

57 points by bryan0 21 days ago | 42 comments

An Annenberg EdWorkingPapers research paper page on a two-year school experiment evaluating AI tutoring with Khan Academy's Khanmigo.