Re:Two things LLM coding agents are still bad at
by bryantnyc on Thursday October 09, 2025 @08:39PM
(#45534453)
"...very subtle and silently introduced mistakes are quite dangerous..."
In my view these perfectly serve the purpose of encouraging you to keep burning tokens for immediate revenue as well as potentially using you to train their next model at your expense.
In my view these perfectly serve the purpose of encouraging you to keep burning tokens for immediate revenue as well as potentially using you to train their next model at your expense.