AI agent benchmarks are broken(ddkang.substack.com)

167 points by neehao 1 year ago | 79 comments

Artificial Analysis Intelligence Index v5.0(artificialanalysis.ai)

35 points by scooby7430 5 days ago | 15 comments

Artificial Analysis's methodology page for its Intelligence Index v5.0, detailing the nine evaluations, category weightings, testing parameters and prompt templates used to rank LLMs.

Efficient LLM Inference (2023)(artfintel.com)

87 points by inaciom 2 years ago | 9 comments

What's working for YC companies since the AI boom(jamesin.substack.com)

122 points by jseidel 1 year ago | 83 comments

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

68 points by jp8585 10 months ago | 66 comments

GLM-5.2 is a step change for open agents(interconnects.ai)

344 points by vantareed 4 months ago | 197 comments

Nathan Lambert's Interconnects post arguing that the GLM-5.2 model marks a capability threshold for open-weight agentic AI.

Artificial intelligence is losing hype(economist.com)

453 points by bx376 2 years ago | 663 comments

An Economist Free exchange column arguing that artificial intelligence is losing hype and asking whether that signals the technology will eventually succeed.

AI tools are spotting errors in research papers(nature.com)

555 points by kgwgk 1 year ago | 200 comments

Nature news article on a growing movement using AI and large language models to detect errors in research papers, sparked by a flawed black plastic utensils study.

Artificial Analysis Intelligence Index v5(artificialanalysis.ai)

52 points by hn-aarvin 5 days ago | 77 comments

Artificial Analysis announces Intelligence Index v5, a composite LLM benchmark adding new private evaluations, with results ranking frontier and open-weights models plus a new Progress Index.

Computers Cannot Make Decisions(wiki.cateat.fish)

175 points by heavensteeth 23 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.

Neural networks are clean(already-clean.goodfire.com)

768 points by themgt 18 days ago | 300 comments

An informal research essay by Nick Cammarata at Goodfire arguing polysemanticity stems from fixable issues, not superposition, making neurons interpretable at scale.

Quality non-fiction books are the antithesis of AI slop(resobscura.substack.com)

463 points by benbreen 3 months ago | 222 comments

Benjamin Breen's Res Obscura essay arguing quality non-fiction books counter AI slop, introducing a vibe-coded tool indexing prize-winning books.