Liquid releases d1.2
Liquid AI’s d1.2-ultra delivers one-ninth the calibration error of GPT-6 Luna across 22,505 questions.
Liquid AI’s d1.2-ultra delivers one-ninth the calibration error of GPT-6 Luna across 22,505 questions.
Tell us what you're building
It's not surprising but is very cool that there's a new decision model that supports audio input. The five new question types that return more variable kinds of output (e.g., many bounding boxes and every passage of text of a type) are a bit more surprising to me, and very exciting. There seem to be no barriers to a world where there are custom questions to handle many, many kinds of use cases at decision-model-level cost and latency.
I haven't tested those new question types yet but have done some preliminary testing of audio, and in a fairly challenging domain: drilling trivia, where there's lots of "uh" and "um," niche vocabulary, proper names, and non-English words. d1.2 has been impressive so far. I plan to exercise this use case a lot more.