Tal Schuster

🥁Introducing Gemini 2.5, our most intelligent model with impressive capabilities in advanced reasoning and coding.

Now integrating thinking capabilities, 2.5 Pro Experimental is our most performant Gemini model yet. It’s #1 on the LM Arena leaderboard. 🥇

Making LLMs run efficiently can feel scary, but scaling isn’t magic, it’s math! We wanted to demystify the “systems view” of LLMs and wrote a little textbook called “How To Scale Your Model” which we’re releasing today. 1/n

*Relaxed Recursive Transformers*
by @talschuster.bsky.social et al.

Converts pre-trained transformers to a more efficient version by turning blocks of layers into a single layer which is iterated. Lots of interesting tricks!

arxiv.org/abs/2410.20672

Will be at NeurIPS. Reach out if you're interested in discussing adaptive compute in LLMs or other topics

New Gemini model grabs first place in all domains.

Happy one year anniversary Gemini team!

Blue sky, green grass, bicycle looks good, bird riding it is almost recognizable as a pelican

Google just released a new Gemini model - gemini-exp-1206

I upgraded my llm-gemini plugin to support it and then got the best result yet for my "Generate an SVG of a pelican riding a bicycle" benchmark

simonwillison.net/2024/Dec/6/g...

Lol

Dear algorithm,
I would like to view:
70% new ML and LLM research and cool results.
10% funny videos with cute animals.
5% sports (but no spoilers if I'm planning to watch the reply later).
5% travel and life hacks.
5% general tech.
5% random.
Regards,