brianjeong

4 miesiące temudiscuss

These margins are far greater than the ones Dario has indicated during many of his recent podcasts appearances.

6 miesięcy temudiscuss

question with the article's main thesis. If agents were trained on human-generated data and "subtracted" human conventions (markdown, file systems, git), is there really such a thing as "native" agent UX that's different from human UX? Or have we just discovering which human conventions happen to align well with transformer attention patterns?

brianjeong

6 miesięcy temudiscuss

You could say the same about Pokemon - the models still struggle quite a bit.

brianjeong

6 miesięcy temudiscuss

I think there's a somewhat valid perspective that the Nth+1 model can simply clean up the previous models mess.

Essentially a bet that the rate of model improvement is going to be faster than the rate of decay from bad coding.

Now this hurts me personally to see as someone who actually enjoys having quality code but I don't see why it doesn't have a decent chance of holding

comments