liamlaverty
Joined 2 years ago
Karma
9
Submissions
6
Member since
Apr 22
Recent submissions
Comment · 4 months ago
Comment · 5 months ago
Anthropic have been using their Claude 4.5 & 4.6 series models to automate searching for security issues. Their approach seems pretty expensive, so I've demonstrated getting a lot of the same benefits on a much lower budget in the Umbraco-CMS repository.
Comment · 5 months ago
I've been trying to get some language models to paint one stroke at a time for a few months now. I thought this community would be interested to see the results.
The article runs through my findings, and there's a linked technical rundown of how the app was built. There's also an interactive gallery [0] of my attempts. You can point an agent at the API docs [1], and they might (ymmv) do a painting themselves.
[0] https://www.liamlaverty.com/paint-by-language-model/ [1] https://www.liamlaverty.com/paint-by-language-model/draw/api
I gave this approach a shot over the first few months of this year[1] (although my director didn't have any custom training). The results were interesting, but I'd not call them "art", since they're low-quality derivative pieces. With reasoning traces enabled, you can see that there's not much intent going on. Though they do attempt to include "incidental objects" to reinforce meaning, like in this jungle scene[2].
[1] https://news.ycombinator.com/item?id=48105385
[2]https://www.liamlaverty.com/paint-by-language-model/inspect/...