Ok, gemini 1.5 is really really good. seriously the most impressive jump i've seen in models in a while when it comes to long context just tried with a paper and asked it "what does Figure 5 show?" it contextualized the whole thing and answered based on that tiny section +
@oriolvinyalsml
-
Gemini 1.5 Pro: In-Context Learning Outperforms Fine-Tuning
By
–
I've been testing Gemini 1.5 Pro's reasoning capabilities this morning. It's near-GPT-4-level with regular prompts. BUT Gemini's performance improves as I add dozens of examples. There doesn't seem to be an upper limit. Many-example prompting is the new fine-tuning.
-
Gemini 1.5 Passes Complex RPG Character Generation Test
By
–
A hard test of Gemini 1.5 that every other AI has failed. I gave it a truly over-the-top RPG (the 352 page rulebook for 60 Years in Space) and asked it to role up a character The instructions are scattered across many pages, and are very complicated, but Gemini seemed to get it.
-
Gemini 1.5 Pro Self-Implements Support in Open Source Codebase
By
–
I showed Gemini 1.5 Pro the ENTIRE Self-Operating Computer codebase, and an example Gemini 1.5 API call. From there, it was able to perfectly explain how the codebase works… and then it implemented itself as a new supported model for the repo! Not perfect, but very close.
-
Gemini 1.5 Pro Launch Highlights Community AI Interactions
By
–
Gemini 1.5 Pro launched last week and already we're seeing the community produce some amazing interactions with long context. Below are some highlights and cool posts from folks who have gotten early access. A few thoughts from discussions / reactions from the community so
-
Gemini 1.5 Pro’s 1M Token Context: 6 Impressive Capabilities
By
–
Gemini 1.5 Pro's 1,000,000+ token context length is incredible. I got early access and spent my Saturday night running tests. Here are 6 impressive capabilities I found:
-
Gemini Advanced Multimodal Capabilities Available in AI Studio
By
–
Great test! Gemini Advanced still doesn't have the latest multimodal capabilities, but you can easily play with these in AI Studio.
-
Multilingual Gemini capabilities explained in Catalan
By
–
Multilingual Gemini — a Catalan explanation
-
OpenAI Sora Video Generation: Anatomical Quirks Spotted
By
–
Amazing job from my friends @OpenAI on Sora! Also, sorry if I spoil this video for you, but I can't unsee the cats' 3 front legs 😆 pic.twitter.com/qVWVrbVEiI
— Oriol Vinyals (@OriolVinyalsML) 16 février 2024Amazing job from my friends @OpenAI on Sora! Also, sorry if I spoil this video for you, but I can't unsee the cats' 3 front legs
-
Gemini 1.5 Pro Processes 800K Tokens Three.js Code
By
–
To show what’s possible with the drastically huge context window in Gemini 1.5 Pro, we prompted it with the three.js examples code – over 100,000 lines of code/800k+ tokens!
— Oriol Vinyals (@OriolVinyalsML) 15 février 2024
(That’s not even the max, it can handle millions of tokens 😀)
Gemini was able to process all the code… pic.twitter.com/N2VYgn2JFJTo show what’s possible with the drastically huge context window in Gemini 1.5 Pro, we prompted it with the three.js examples code – over 100,000 lines of code/800k+ tokens! (That’s not even the max, it can handle millions of tokens ) Gemini was able to process all the code