Maybe I’m being very naive, but why can’t LLMs audit smart contracts? Feels like there’s plenty of public data for the models to be trained on.

Maybe I’m being very naive, but why can’t LLMs audit smart contracts? Feels like there’s plenty of public data for the models to be trained on. https://warpcast.com/polluterofminds/0x0a371693

Writer. Building @pinatacloud. Tinkering with a Farcaster native alternative to GoodReads: https://readcast.xyz \ https://polluterofminds.com

I think it’s that not all of the public contracts it’s trained on are secure

Builder of software and songs. 

Music, Blog, Website: https://www.mattlee.world/links

Sure, but any mistakes in auditing those examples would be carried downstream and any novel functionality would need to be reaudited (also I have no idea what I’m talking about just guessing)

Couldn’t you fine tune on specific exploit examples to improve the reliability?