@JeremiahThinks@swyx@emilkowalski None of it. It’s clearly a compilation of his blog posts and lessons compacted into a LLM friendly format.
What do you think of the “Core Philosophy” section? Is it a good use of tokens? Will it create a meaningful difference in output?
@JeremiahThinks@swyx@emilkowalski None of it. It’s clearly a compilation of his blog posts and lessons compacted into a LLM friendly format.
What do you think of the “Core Philosophy” section? Is it a good use of tokens? Will it create a meaningful difference in output?
@swyx@emilkowalski The explicit instructions are great but can output improve by invoking a certain kind of mindset? Do agents need the core philosophy, or do humans?
“You are an expert artist from the Japanese collective Jikken Koubou. Form follows function. The medium is the message. Be curious”
@swyx@emilkowalski The explicit instructions are great but can output improve by invoking a certain kind of mindset? Do agents need the core philosophy, or do humans?
“You are an expert artist from the Japanese collective Jikken Koubou. Form follows function. The medium is the message. Be curious”
I am depressed about AI vibe-slopping because we programmers used to own the code we wrote, we used to talk to another and we used to be more explorative.
With AI, you are discouraged from using less known libraries or approaches, AI just gravitates towards the mean
Kind of embarassing to admit but I only just recently replaced `execCommand` for textarea undo/redo with my own undo management library.
Works well except I still haven’t figured out how to preserve scroll position after the window is resized
Interviewer : what’s your biggest strength?
Me as an developer : Machine Learning
Interviewer : what’s 6 + 9 ?
Me : 0
Interviewer : Incorrect. It is 15
Me : It’s 15
Interviewer: what’s 5+20 ?
Me : it’s 15
Apple intentionally sabotaged the pattern by changing clamping order from post to pre compositing after I spoke of it publicly. It’s still broken on the web today https://t.co/h5nudujrYG