On agents
- Taste without a verifier
Coding agents somehow learned to build good-looking websites, although nothing checks whether a design is beautiful. What video editing can borrow from that: preference models, critics and loops.
2 min reads likes comments - What a video editing agent needs to get right
I built an agent that edits my social videos end to end using knowledge of my personal taste. What that asks of the timeline, the feedback loop and the product.
4 min reads likes comments - GPT-4o hears you laugh
OpenAI and Google both showed real-time multimodal assistants this week. Speech as a native modality changes what a conversation with a model is, and latency turns out to be the feature.
2 min reads likes comments - The model rewrites your prompt
DALL·E 3 in ChatGPT doesn't use what you typed. It has a language model write a long, detailed prompt for you. Creative tools are turning into agents that interpret intent.
2 min reads likes comments - It learned Minecraft by watching YouTube
OpenAI's VPT labeled 70,000 hours of Minecraft videos with the actions players took, using a small model trained on a little labeled data. Passive video became interaction data.
2 min reads likes comments - One network, 604 tasks
DeepMind's Gato plays Atari, captions images, chats and stacks blocks with a real robot arm, all with the same weights. Turning actions into tokens is the interesting part.
2 min reads likes comments