News for hackers. Stuff that matters.
Re:Introducing Gemma 3n by simonw on Thursday June 26, 2025 @07:30PM (#44392472)
It was supposed to be a joke. But weirdly it turns out there's a correlation between how good a model is and how good it as at my stupid joke benchmark.

I didn't realize quite how strong the correlation was until I put together this talk: https://simonwillison.net/2025/Jun/6/six-months-in-llms/

Re:Introducing Gemma 3n by moritzwarhier on Friday June 27, 2025 @03:58AM (#44394731)
Always loved this example, what do you think of ASCII art vs SVG?

Since it's not a formal encoding of geometric shapes, it's fundamentally different I guess, but it shares some challenges with the SVG tasks I guess? Correlating phrases/concepts with an encoded visual representation, but without using imagegen, that is.

Do you think that "image encoding" is less useful?

It's a thing I love to try with various models for fun, too.

Talking about illustration-like content, neither text-based ASCII art nor abusing it for rasterization.

The results have been interesting, too, but I guess it's less predictable than SVG.

Re:Introducing Gemma 3n by simonw on Friday June 27, 2025 @08:16AM (#44396194)
I've had disappointing results with ASCII art so far. Something I really like about SVG is that most models include comments, which give you an idea of what they were trying to do.
Re:Introducing Gemma 3n by moritzwarhier on Friday June 27, 2025 @01:17PM (#44398546)
Yes, the comments part makes sense, you also included it in the talk (I read the transcript but forgot to mention it in my comment, sorry :)

It makes sense, since it works adds associations between descriptions and individual shapes / paths etc., similar to other code.

Re:Introducing Gemma 3n by throw0363fc53 on Saturday June 28, 2025 @11:41AM (#44405499)
No way *wink*, our DevRel don't push for a good outcome on this one test case to get positive coverage on the top independent blog read by LLM people!

https://simonwillison.net/2025/May/20/google-io-pelican/