Are AI labs pelicanmaxxing?(dylancastillo.co)

632 points by dcastm 3 months ago | 237 comments

Blog post investigating whether AI labs are optimizing their LLMs for Simon Willison's 'SVG of a pelican riding a bicycle' informal benchmark.

LLM research on Hacker News is drying up(dylancastillo.co)

21 points by dcastm 6 months ago | 5 comments

Stateless MCP has recaptured my interest(simonwillison.net)

360 points by tosh 2 months ago | 204 comments

Simon Willison blog post on the stateless MCP 2.0 specification release and the mcp-explorer and datasette-mcp tools it inspired him to build.

My finetuned models beat OpenAI's GPT-4(mlops.systems)

376 points by majc2 2 years ago | 86 comments

Blog post evaluating finetuned Mistral, Llama3 and Solar LLMs against OpenAI's GPT-4 on accuracy for structured data extraction from press releases.

Experimentation Matters: Why Nuenki isn't using pairwise evaluations(nuenki.app)

4 points by Alex-Programs 1 year ago | 0 comments

ChatGPT is NOT a LLM – GPT is(vincirufus.com)

14 points by vincirufus 1 year ago | 11 comments