Launch: llm-gemini 0.34
New mannequin gemini-3.8-flash for Gemini 3.8 Flash, with low, medium and excessive pondering ranges. #146
Mounted async responses failing to document the resolved mannequin model. Thanks, Charlie Tonneslan. #137
Google launched Gemini 3.8 Flash (and three.8 Flash Cyber, however that is out there to “trusted defenders” solely) at the moment.
Listed here are the pelicans for prime, medium, and low. That is excessive:
For comparability, listed below are the identical pelicans generated utilizing Gemini 3.7 Flash.
One thing I recognize about Gemini Flash is that it is quick, low-cost, and competent at issues like HTML and JavaScript. I used to be messing round with it and prompted “make me a cool factor in html” and it constructed this, which is actually a cool factor in HTML! Took 13 seconds, value 1.8 cents.
Your browser doesn’t help HTML5 video.
Should you click on by way of to the demo you may see yet another factor I constructed with Gemini 3.8 Flash.
My markdown-svg-renderer device lets me feed within the URL to a Gist with Markdown in and renders that markdown with fenced code blocks for SVG accurately rendered.
I used Gemini 3.8 Flash (with my very primary llm-coding-agent coding agent plugin) so as to add help for HTML as effectively, so now any HTML blocks within the Markdown are rendered utilizing a sandboxed iframe. Here is the transcript.
Tags: ai, generative-ai, llms, llm, gemini, pelican-riding-a-bicycle, llm-release
