Antoine Leblanc (@nicuveo@tech.lgbt)
tech.lgbt
oh my god i had missed this from the postmortem, but the way they validated the test queries they ran (asking the LLM for explanations of code samples) was... TO FEED THE RESULTS INTO GPT-4 AND ASK IT TO CLASSIFY THEM AS "ACCURATE" OR "INACCURATE". THEY ONLY REVIEWED SOME OF THE ONES LABELLED AS "INACCURATE". i want to scream. at least, i feel vindicated for engaging in the thread despite not being a heavy MDN user, because it is extremely apparent that they have no idea what they're doing.

see also the github thread linked in the mastodon post, where the couple of gormless AI hypemen responsible for MDN’s AI features pick a fight with like 30 web developers

from that thread I’ve also found out that most MDN content is written by a collective that exists outside of Mozilla (probably explaining why it took them this long to fuck it up), so my hopes that somebody forks MDN are much higher