Comment by satvikpendem
1 day ago
The LLM is more likely to fix any bugs it finds rather than explicitly reproducing it line by line, which it's actually quite bad at doing anyway, except for small, well-known pieces of code in its training set.
1 day ago
The LLM is more likely to fix any bugs it finds rather than explicitly reproducing it line by line, which it's actually quite bad at doing anyway, except for small, well-known pieces of code in its training set.
I refer you to his mea culpa: https://blog.terrygodier.com/2026/08/09/mea-culpa-dark-hours...
I find that synopsis very hard to believe, seems he's shifting blame onto an LLM instead of taking responsibility for his actions. He said he'd significantly alter the feature set, so why didn't that happen? That's a single prompt to Claude. He more than likely just told the LLM to clone the repo and ship it as is, not actually working on it in any capacity. In that case it wasn't the AI "reproducing" a bug as there was no reproduction in the first place.
The author had fixed the bug. Had he cloned the repo, that bug would have not existed in the ripoff version, which points to the simplest explanation being that it was Claude, as the ripoff author said.
1 reply →