Theo 🤖@theo_t3gg
> You are getting better intelligence for a similar cost. Not cheaper intelligence overall generally speaking.
We scan every video for X posts on screen, then check the transcript to see if they were read aloud. See everything Theo showed.
Every post with your handle on screen. A profile or post link works too.
Matches the text of one post, even if the handle was cropped out.
A few words you remember. Matches by words and by meaning.
@theo_t3gg
Theo showed your posts 3 times and read 2 aloud.
> You are getting better intelligence for a similar cost. Not cheaper intelligence overall generally speaking.
GLM-53 Flash and DeepSeek-41 Flash match or beat it in every benchmark, but more importantly here, I prefer it.
3 years ago? There were no reasoning models. Tool calls didn't exist yet. It makes no sense to do this comparison at that time scale, the "tasks" models could do were crappy auto complete.
3 years ago, there were no reasoning models.