just spent an hour helping a friend debug some lovable-generated code. he's on hour 6 with this bug

super bearish on vibecoding with llms. they're great for prototyping but cannot be trusted

we need a different model architecture that can actually understand and reason about the code

building /cabin, advising /clanker and /farcon | grin.io

Anthropic CEO, Dario Amodei

in the next 3 to 6 months, AI is writing  90% of the code, and in 12 months, nearly all code may be generated by AI https://t.co/PQVh3gM7kt

Haider.

Elevating onchain creators @brightmoments @ampsfun @nodefoundation

https://x.com/slow_developer/status/1899430284350616025?t=4I-tMyCkxMMmjicieCpRUw&s=08

i agree with this. ai helps you write tons more code way faster

but that doesnt change my contention that it doesnt have a real understanding of the code and is bad at explaining and debugging it (though feeding linter/compiler errors back into itself goes a long way)