Hacker News Reader

Comment by simonw | Hacker News Reader

I added support to these models to my llm-gemini plugin, so you can run them like this (using uvx so no need to install anything first):

  export LLM_GEMINI_KEY='...'
  uvx --isolated --with llm-gemini llm -m gemini-flash-lite-latest 'An epic poem about frogs at war with ducks'

Release notes: https://github.com/simonw/llm-gemini/releases/tag/0.26

Pelicans: https://github.com/simonw/llm-gemini/issues/104#issuecomment...

View on HN

I wonder if [good examples of] SVGs of pelicans on bikes are "being introduced" into training sets. Some of the engineers who work on this stuff are the kind to hang out here.

It's possible, but honestly I've never seen a decent vector illustration of a pelican on a bicycle myself so they'd have to work pretty hard to find one!

They could just ask a designer to do a few bespoke illustrations, then generate synthetic data from that, right? Have an image model generate a set of variations, then convert them to SVG.

But looking at these images, Google clearly hasn’t done that yet.

Yeah, the dedicated image generators can produce really good pelicans riding bicycles now, and you could trace one of those into a vector SVG as training data.

I don't think it would be worth it though, it would be pretty obvious you had cheated on my benchmark when it drew a perfect pelican riding a bicycle and then failed at a flamingo on a unicycle.

Who wins in the end? the frogs? the ducks? or the pelicans?

I heard the dragon took the pole, but it may have been wind-aided.

This depends on the value of your LLM_GEMINI_KEY!

Reply on news.ycombinator.com