Damus
Vitor Pamplona profile picture
Vitor Pamplona
@VitorPamplona
One of the coolest shifts in coding is the ability to ask 5 different AI sessions to write 5 different solutions, then run them all side-by-side as a full app to see proof of what actually performs best.

This could never have happened before AI.

If you are a dev and you are still guessing which methods work better or going by your own feeling or intuition, you are not prepared for the level of scrutiny of your code that is about to come.
114❤️8❤️3✅️1🎯1👍1💙1
Ghost👻 · 8w
And, if I don't code🤔? (I don't my the way😬).
Nuts · 8w
5 apps and 5 completely different test harness? You have too much tokens to burn
Infinity x2 · 8w
yup the cost of experimentation has become so low, its crazy
Jeroen ✅ · 8w
nostr:nprofile1qqsqvcu68pkfcyq5y9mz9n9u7sys33835rpnuglc6mtg7j4lv40c7ugfe0raa
AU9913 · 8w
I am not prepared, but blame management. I've done so much on my own, but it would go a long way to block 8am-noon on Friday off for tool dev and research instead of all of this piddly shit.
sister_sam · 8w
How is it yours if the AI writes it all? If it evaluates it too for which is best then who needs you?
I)ruid · 8w
Yup. My coding agent does A/B testing all the time. It's also how we evaluate different coding models for adoption.