logoalt Hacker News

siva7yesterday at 9:48 PM3 repliesview on HN

people read a bit more about transformer architecture to understand better why telling what not to do is a bad idea


Replies

computomaticyesterday at 9:57 PM

I find myself wondering about this though. Because, yes, what you say is true. Transformer architecture isn’t likely to handle negations particularly well. And we saw this plain as day in early versions of ChatGPT, for example. But then all the big players pretty much “fixed” negations and I have no idea how. So is it still accurate to say that understanding the transformer architecture is particularly informative about modern capabilities?

show 1 reply
II2IIyesterday at 11:15 PM

I'm not sure that advice is effective either.

I use an LLM as a learning tool. I'm not interested in it implementing things for me, so I always ignore its seemingly frantic desires to write code by ignoring the request and prompting it along other lines. It will still enthusiastically burst into code.

LLMs do not have emotions, but they seem to be excessively insecure and overly eager to impress.

arbolesyesterday at 10:11 PM

Please elaborate.

show 2 replies