Ethan He
speaker
722 appearances
1 recordings
1 series
first heard Jun 2026
last heard 1 Jun
Ethan He’s voice in public audio — every appearance, attributed to the second.
Trend
recordings per month · last 12 monthsRecordings per month over the last 12 months — 1 in all, peaking in Jun 2026 with 1.
Appearances
Yeah, it's interesting to see that because the video model's capability increase actually come from language model being more intelligent.
I think video agent, like it can unlock more capabilities
stuff that you might imagine.
So there's a few things.
So one thing is when we are prompting these models, so most of the people were actually not very good at prompting.
Actually, language models have a better sense of how to prompt AI models.
AI models know AI models better.
So if you jointly train these models, maybe as a model, have a better sense of how to prompt each model.
Like a different model might be different.
Another thing is, it might not as simple as just like generate a few clips and slap them together using FFmpeg.
There might be...
more image and video editing to appear in this process.
Say, if you want to exactly add a blob of text at this time step, the video models might not get that intention.
very precisely.
But these are possible using these deterministic tools.
The video agents can use all sorts of tools, so you don't have to put all of the capabilities into the transition model itself.
I guess by the end of this year, this is going to be a big hit.
So the inflection point will be where the videos generated by video agents can get to production-grade quality.
It can be presented and it can be distributed in ads.
And once that happens, I think the enterprise will have much more budget for video models because the agents are inherently more expensive than the other video models themselves because they do this iterative process.
Showing 621–640 of 722 · page 32 of 37
← Previous
Next →