@Kensan @ela Definitely, the irony is that the same LLM can sometimes spot bugs in the code that it produced...which shows another defect / weakness of current LLMs. You might ask it to produce code that solves problem X and it will with high likelihood produce whatever was prevalent in the training (including bugs), but not connect it directly to knowledge about how this is a bad idea (unless instructed so by training / finetune / prompt eng.).

@ela hehe next weekend :P but jokes aside: the bad practices or even insecure coding patterns encoded into current LLMs will hurt us in the future big time...it's no fun to fix something today, only to have a coding agent introduce the same issue everywhere again next day. Something that model creators should put more focus on.

@cynicalsecurity Likely all Overleaf

@ela Seems like scary and interesting/fascinating often go hand in hand when it comes to technology...For the training of juniors I can only imagine that some skills and education will just become obsolete, others will just be lost (someone compared the Linux kernel to the pyramids where future scientists will be puzzled how someone could build them without modern tools).. On the upside, the snakeoil seems to be hit much harder for now!