@maybeTuring Coding with AI is like walking into a store where suddenly half the store costs 1¢. There's such an urge to just throw everything cheap into the cart at once but at some point you gotta remember that you had a shopping list when you first came in.
As software systems grow, understanding them becomes fragmented across people and tools. No single artifact captures how the system actually behaves.
We describe the model we’ve been building at Antimetal to make this implicit understanding explicit and machine-legible.
https://t.co/fJPEbqObEX
If you couple this with voice input, I can very easily go through a few posts and give detailed feedback on each in less than a minute; it means no longer relying on inferences about the categories or collaborative filtering to guess at user preference.
Recommendation engines based on "show more / show less like this" are already feeling outdated. With LLMs we're starting to enter an era where we can just tell our computer what we like and why we like it and the computer will actually understand.
The ergonomics of running large data jobs via @modal_labs is seriously my platonic ideal of this kind of workflow and a thing I wish I had years ago. It's a truly excellent realization of devx as a product. https://t.co/QZaYbChZaw
Updated my username on a whim from @146 but just realized I can never change it back because of the minimum username requirement on Twitter now. Looks like @146 is gone forever now...
Although I am a Buddhist monk, I am skeptical that prayers alone will achieve world peace. We need instead to be enthusiastic and self-confident in taking action.