Honestly, this has got to be one of the gutsiest one-man AI stunts I’ve seen.
Like—going up against 10 big models at once, making it look like some kung fu battle, and then just dropping all the data out in the open? That’s kinda nuts (in a good way).
So, which model surprised you the most? Did any of them totally flip your prompt in a way you didn’t see coming?
does TXT OS work equally well with open-source models, or is it optimized more for models like GPT-4 or Claude?