Matthew Berman and colleagues discuss personal agent tools and compare their experiences with different subscriptions and workflows. During the live session, Berman starts several Kimi K3.1 testsEvaluation is the systematic assessment of a system's behaviour or results against explicit criteria. prompted by viewers.
The group reviews model-generated motion graphics, videoAI-generated content is text, imagery, audio, video, code, or other material produced substantially by a generative AI system. and a game, and informally compares a knot animation with another model. Their early impressions and benchmark reactions are subjective, not systematic measurements.
Watch on YouTube
