First screen, captured .
Looks similar
My finetuned models beat OpenAI's GPT-4(mlops.systems)
376 points by majc2 | 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.
Are AI labs pelicanmaxxing?(dylancastillo.co)
632 points by dcastm | 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.
Related stories
How I use LLMs to learn complex topics(laurentiugabriel.github.io)
763 points by laurentiurad | 489 comments
Personal blog post by Laurentiu Raducu describing how he uses LLMs to learn complex topics, including building an interactive chip-making game called ChipTycoon.
LLMs use a surprisingly simple mechanism to retrieve some stored knowledge(news.mit.edu)
336 points by CharlesW | 121 comments
MIT News article on research showing LLMs often retrieve stored facts via simple linear functions, and a technique to probe what a model knows about subjects.
Can gzip be a language model?(nathan.rs)
384 points by networked | 149 comments
A blog post by Nathan Barry exploring whether gzip compression can be used as a language model to generate text, with an interactive beam search demo.
As an experienced LLM user, I don't use generative LLMs often(minimaxir.com)
335 points by minimaxir | 183 comments
Max Woolf's blog post describing how he, as an experienced data scientist and LLM tool developer, actually uses generative LLMs only sparingly in his work.
Why Janet?(ianthehenry.com)
344 points by ianthehenry | 112 comments
Ian Henry's blog post making the case for the Janet Lisp dialect as a simple, fun language for side projects, promoting his free book about it.
An LLM is a lossy encyclopedia(simonwillison.net)
450 points by tosh | 304 comments
Short blog post by Simon Willison proposing the analogy that an LLM is a lossy encyclopedia, and advising users to supply correct examples rather than rely on recall.