Re:As an experienced LLM user, I don't use generative LLMs o...
by gnatolf on Monday May 05, 2025 @03:58PM
(#43898860)
The churn of staying on top of this means to me that we'll also chew through experts of specific times much faster. Gone are the day of established, trusted top performers, as every other week somebody creates a newer, better way of doing things. Everybody is going to drop off the hot tech at some point. Very exhausting.
Re:As an experienced LLM user, I don't use generative LLMs o...
by Philpax on Monday May 05, 2025 @04:52PM
(#43899342)
The answer is simple: have your AI stay on top of this for you.
Mostly joke, but also not joke: https://news.smol.ai/
Re:As an experienced LLM user, I don't use generative LLMs o...
by arthurcolle on Monday May 05, 2025 @02:27PM
(#43897942)
I like using Jupyter Console as a primary interpreter, and then dropping into SQLite/duckdb to save data
Easy to to script/autogenerate code and build out pipelines this way
Re:As an experienced LLM user, I don't use generative LLMs o...
by red_hare on Monday May 05, 2025 @03:27PM
(#43898540)
It is a little crazy how fast this has changed in the past year. I got VSCode's agent mode to write, run, and read the output of unit tests the other day and boy it's a game changer.
I see people getting LLMs to generate code in isolation and like pasting it into a text editor and trying it, and then getting frustrated, and it's like, that's not how you're supposed to be doing it anymore. That's 2024 praxis.