“The grabbing a drink task is just how we test language following ... you can just specify what you want if the model follows intent follows instruction”
♫
Said on Latent Space: The AI Engineer Podcast
Latent Space: The AI Engineer Podcast · Dyna-2: General Purpose Physical Agents with Hour-Long Autonomy - Jason Ma, Dyna Robotics
Audio streams from the publisher’s own feed. Verbatim does not host or copy it.
fine-tuned the general world-action model on a handful of task-specific demonstrations (few-shot) to enable new tasks like pulling drinks from a fridge
“The grabbing a drink task is just how we test language following ... you can just specify what you want if the model follows intent follows instruction”
“You may need a bit of fine-tuning of your probes so that they work on each person's particular fine-tuned model”
“We asked inkling to fine tune itself using tinker. The model wrote its own fine tuning job, ran it and evaluated the result.”
“These new beverage types have been huge for the industry… they invented new reasons for us to not drink water and spend money on their beverages instead.”
The strongest new moments on your topics, in the speakers' own words. Free for three topics.
No card. No password. One-click unsubscribe.
Pro watches up to 25 names or phrases and emails you the morning after they are said.
See Pro, $29 a monthVerbatim quotes a short extract and links to the episode; the episode belongs to its publisher. Remove a show.