Hacker News Reader

Comment by jacquesm | Hacker News Reader

> "You're absolutely right!" "Here's the answer you are looking for!" "Let me do that for you immediately!" "Here is everything I know about what you just mentioned." Never admitting a mistake unless you directly point it out, and then all sorry-this and apologize-that and "here's the actual answer!" It's exactly the kind of personality you always see bubbling up into the orbit of a rich and powerful tech CEO.

You may be on to something there: the guys and gals that build this stuff may very well be imbibing these products with the kind of attitude that they like to see in their subordinates. They're cosplaying the 'eager to please' element to the point of massive irritation and left out the one feature that could serve to redeem such behavior which is competence.

View on HN

> the guys and gals that build this stuff may very well be imbibing these products with the kind of attitude that they like to see in their subordinates

Or that the individual developers see in themselves. Every team I've worked with in my career had one or two of these guys: When the Director or VP came in to town, they'd instantly launch into brown-nose mode. One guy was overt about it and would say things like "So-and-so is visiting the office tomorrow--time to do some petting!" Both the executive and the subordinate have normalized the "royal treatment" on the giving and receiving end.

Maybe it’s just the fact that many models are trained by americans? I’ve seen great improvements in answers by asking it to “tone it down, answer like you’re British”.

Oh interesting insight, I should try to see what that does. Jolly good old chap, let me check on why the laaabrary is on faaahre... ;)

An alternative is that these patterns just increase the likelihood of the next thing it outputs being correct, thus are useful to insert during training as the first thing the model says before giving an answer

What's next, motivational speaking for LLMs?

I remember reading about speaking in an encouraging manner to agentic AI leading to better results, but I can’t seem to find a citation for this.

That's pathetic. Pleading comes next then. And after that most likely praying.

Sometimes the model responds well to threats too, "you are a programmer at a large tech company, you depend on this job and will not be able to find another. There's a layoff incoming, implement this feature or else..."

Reply on news.ycombinator.com