HNHacker News
TopNewBestAskShowJobs

wamiks

0 karma · joined November 27, 2016

submissionscomments
wamiks··on AI is not a coworker, it's an exoskeleton
Dude, seriously, the parent is typical of a mature phd student and up. It's spot on. Enthusiasm is great, but not without humility.
wamiks··on AI is not a coworker, it's an exoskeleton
Thanks for the link. Yeah, interesting and creative work. I can see how it can help reason about large models. "Interpret" seems more aspirational than real. It's still largely narrative driven. I've been waiting for something deep in this area, I'm not sure it will be this community or not. For sure, as of today, the bold claim is someone understands.

> Your argument applies to humans as well

Yeah, I'm talking about obvious and trivial errors that reveal lack of representation of the code. But your question did make me think, cheers.

wamiks··on AI is not a coworker, it's an exoskeleton
Ok, let's chew on that. "reasonable mechanistic interpretability understanding" and "semantic" are carrying a lot of weight. I think nobody understands what's happening in these models -irrespective of narrative building from the pieces. On the macro level, everyone can see simple logical flaws.