[bad_username]

> furiously hammering on my laptop “WHAT THE FUCK DID YOU DO???”. The recipient of these tirades is, you might have guessed, a coding agent. It’s completely pointless, I know.

I believe it's worth than pointless. IMO adding such things to the context "configures" the AI to reproduce the statistics of conversations where people swore, shouted, and were unprofessional (despite the alignment runing and all that), where quality content is rarer to find. So this is bound to decrease the quality of the LLM output.

[buu700]

Agreed. These accounts of people having genuine emotional responses to LLM chats, even going as far as to spend tokens berating them, are very curious. I would be surprised to learn that SOTA models respond optimally to anything other than dispassionate problem-solving, or that scolding per se serves any productive purpose.

Of course we all swear at our computers every now and then, but for me it's always been in good fun. It's just a sarcastic joke that adds some levity and self-amusement to an otherwise arduous debugging process, not generally actual insinuation of malfunction (or malice) on the part of the hardware/OS/toolchain. I'd assumed that "half the job is cursing at the machine until it obeys you" was a big in-joke amongst the profession, but the LLM era seems to be exposing a divide in how tongue-in-cheek that statement really is.

[astrange]

That's how a base model would work. An assistant model is simulating a human and behaves the same way a human would if you screamed at them.

https://www.anthropic.com/research/emotion-concepts-function

[JSR_FDED]

Why would you deprive the LLM of a signal that indicates how badly it screwed up?

[carsareok]

Because it's a completion engine and has no notion of "signals".

Swearing was in the texts they were trained on to complete token by token. I suspect it weren't texts with a lot of high-quality reasoning.