Who will be the first LLM provider to publish genuinely useful release notes?
LLMS
-
Overcoming AI Output Token Limits Through Strategic Prompting
By
–
Yeah the maximum number of output tokens is an important factor – but you can overcome that by promoting it for more content and including the content it's already given you
-
Gemini 1.5 Pro API Released with Video Audio Support
By
–
This uses the new Gemini 1.5 Pro API that was released today. It currently only supports listening to the audio content of videos. If anyone wants, please feel free to add support for video frames as well.
-
Gemini Pro 1M Token Context Now Free Without Waitlist
By
–
Gemini Pro with the 1 million token context limit is now available for free and without a waitlist! https://t.co/eiNsXCBMBU
— Simon Willison (@simonw) 10 avril 2024Gemini Pro with the 1 million token context limit is now available for free and without a waitlist!
-
LLMs Becoming More Persuasive in AI Research Development
By
–
LLMs have been outperforming humans at AI criticism for several years now. It's time that they become a lot more persuasive at AI research
-
Discovering Prompts Behind AI Model Research Paper
By
–
I'm trying to figure out what prompts they used. I think it's these – this is from a paper that their paper links to https://
github.com/lilakk/BooookS
core/tree/main/prompts
… -
Fiction vs Non-Fiction in AI Summary Evaluation Studies
By
–
Looks like all but one of the books in that study were fiction, which I imagine has quite different characteristics when it comes to evaluating summaries than non-fiction https://
github.com/mungg/FABLES/b
lob/main/booklist.md
… -
Training Models and Gemini 1.5 Pro Project Development
By
–
waiting on a few models to train, guess I'll be cooking up some gemini 1.5 pro projects in the meantime
-
#1 Early-Stage Startup Building LLM Apps Today
By
–
We're grateful for the recognition in Enterprise Tech 30 as the #1 ranked Early-Stage Startup! We're on a mission to make it easy to build the LLM apps of tomorrow, today. We're actively hiring across multiple roles including Software Engineer (JS, Python, SDK, &
-
Benchmarking AI Reasoning: Defining Metrics and Testing Improvements
By
–
Benchmarking is especially hard when we don't even agree as to what the words involve mean. I believe that reasoning has been improved, but I am not sure what that actually translates to. The only way to figure out is to put in hours to test yourself?