Huge congrats @27upon2 and the @SemiAnalysis_ team! Awesome work.
It’s cool that Astra/Fable both work around their multi-modal limitations (no native video) by using Swift/Python programs for frame and audio analysis.
If available, they can use FFmpeg too.
I naively imagined that native video understanding would be table stakes but obviously the models can get around this.
2
6
201
James retweeted
Today we’re launching Prompt Adaptation, a state-of-the-art agentic system that automatically adapts prompts across LLMs. Prompt Adaptation outperforms all other methods and significantly improves accuracy over manual prompt engineering, saving you thousands of hours per year.




