The last six months in LLMs, illustrated by pelicans on bicycles
simonwillison.net
The last six months in LLMs, illustrated by pelicans on bicycles
1–10 of 244 posts
Re: The last six months in LLMs, illustrated by pelicans on bicycles
#2My only take home is they are all terrible and I should hire a professional.
Re: The last six months in LLMs, illustrated by pelicans on bicycles
#3I really enjoy Simon’s work in this space. I’ve read almost every blog post they’ve posted on this and I love seeing them poke and prod the models to see what pops out. The CLI tools are all very easy to use and complement each other nicely all without trying to do too much by themselves.
And at the end of the day, it’s just so much fun to see someone else having so much fun. He’s like a kid in a candy store and that excitement is contagious. After reading every one of his blog posts, I’m inspired to go play with LLMs in some new and interesting way.
Thank you Simon!
Re: The last six months in LLMs, illustrated by pelicans on bicycles
#4My only take home is they are all terrible and I should hire a professional.
Most of them are text-only models. Like asking a person born blind to draw a pelican, based on what they heard it looks like.
Re: The last six months in LLMs, illustrated by pelicans on bicycles
#5My only take home is they are all terrible and I should hire a professional.
it depends on quality you need and your budget
Re: The last six months in LLMs, illustrated by pelicans on bicycles
#6My biggest gripe is that he's comparing probabilistic models (LLMs) by a single sample.
You wouldn't compare different random number generators by taking one sample from each and then concluding that generator 5 generates the highest numbers...
Would be nicer to run the comparison with 10 images (or more) for each LLM and then average.
Re: The last six months in LLMs, illustrated by pelicans on bicycles
#7Enjoyable write-up, but why is Qwen 3 conspicuously absent? It was a really strong release, especially the fine-grained MoE which is unlike anything that’s come before (in terms of capability and speed on consumer hardware).
Re: The last six months in LLMs, illustrated by pelicans on bicycles
#8Re: The last six months in LLMs, illustrated by pelicans on bicycles
#9My only take home is they are all terrible and I should hire a professional.
Most of them are text-only models. Like asking a person born blind to draw a pelican, based on what they heard it looks like.
That seems to be a completely inappropriate use case?
I would not hire a blind artist or a deaf musician.
Re: The last six months in LLMs, illustrated by pelicans on bicycles
#10Earlier quoted context omitted.
Most of them are text-only models. Like asking a person born blind to draw a pelican, based on what they heard it looks like.
That seems to be a completely inappropriate use case? I would not hire a blind artist or a deaf musician.
The point is about exploring the capabilities of the model.
Like asking you to draw a 2D projection of 4D sphere intersected with a 4D torus or something.