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

we're like 2-3 months in 

feels like the models will get much better at debugging and helping us mere mortals understand what's actually happening in the code

Stay Curious // iixii // Lazer Technologies // Prev: CoinDesk, Roc Nation // based

fair point.  maybe you're right.  I'm just not underestimating how these tools will improve over time

i dont believe that

all our models are based on transformers and are ultimately token predictors. there's no sense in which they "understand" your code or can model what will happen when they make changes. no amount of finetuning or chain-of-thought-ing is gonna change that

needs a fundamentally new design