News for hackers. Stuff that matters.
Re:Things we learned about LLMs in 2024 by layer8 on Tuesday December 31, 2024 @06:34PM (#42562669)
You are right, but doing all that is incredibly cumbersome, at least to some people, which is why they don’t like working with LLMs.
Re:Things we learned about LLMs in 2024 by simonw on Tuesday December 31, 2024 @06:36PM (#42562681)
That was one of the themes of my article: LLMs are power-user tools, mis-sold as "easy to use". To get great results out of them you need to invest a whole lot of under-documented and under-appreciated effort. https://simonwillison.net/2024/Dec/31/llms-in-2024/#llms-som...
Re:Things we learned about LLMs in 2024 by layer8 on Tuesday December 31, 2024 @07:26PM (#42562941)
It’s not just that you need to be a power user (I certainly am), you also need to be fine with nondeterminism and typing a lot of prose, instead of doing everything with keyboard shortcuts and CLI commands, with reproducible outcomes. It’s a different mode of operation and interaction, requiring a different predisposition to some degree.
Re:Things we learned about LLMs in 2024 by fragmede on Tuesday December 31, 2024 @08:52PM (#42563355)
unless you can type faster than you can talk, (which some people can), stop typing and start dictating. aider has a /voice command for a reason.

I don't use it exclusively, but damn does it help in the right places.

Re:Things we learned about LLMs in 2024 by eterps on Wednesday January 01, 2025 @06:14AM (#42565355)
Can you elaborate, or give some examples? I am having trouble imagining in which situations that would be useful because I tend to put a lot of thought into defining the right prompt before sending it over.
Re:Things we learned about LLMs in 2024 by madmask on Wednesday January 01, 2025 @02:56AM (#42564624)
Exactly! I don’t like talking or writing or explaining.

My mind generally uses language as little as possible, I have no inner monologue running in the background.

Greatly prefer something deterministic to random bs popping up without the ability of recognizing it.

I don’t like llms but sometimes use them as autocomplete or to generate words, like a template for a letter or boilerplate scripts, never for actual information (à la google).