The amount of cargo-culting around AI tooling and practices is so weird to me.

Why not just try and see? The fast feedback loop allow testing all kind of weird theories in a matter of 30m-1h during normal working sessions, most results are obvious

The configuration and workflow space is big, and exploring it isn't fun for most people.

>Why not just try and see?

There is a difference between trying something and performing a test whose results are meant to be representative of most setups. A lot of people (in tech surprisingly) who see themselves as practitioners of applied science, apply flawed methodologies and try to generalise the results.

Just because testing is fast, it does not mean that it is free or cheap. Plus time is money and verifying every LLM setup every koolaid dev is proclaiming on bluesky could easily be a full time job.

I believe is just an impression given “Anti somethings” people are usually more vocal and likely to comment on the topic

Major API changes in things like Svelte have shown that this is actually not as true as we expected it to be.

Simon Willison has an good post about it

I’ve surely spent more time modding PSP than playing games. Zero regrets

I just wish I started getting into software earlier, at that time it felt something super hard for “A beautiful mind” people

We need more tools like QMD that beautifully download and use local models under the hood

https://github.com/tobi/qmd

Expect to see Orhun in here before clicking, not disappointed

300% accurate

Does Better Auth still have the weird design to be everything “request header based”? I remember running admin scripts and tests to be very hacky due to it cause if you skipped that plugins wouldn’t run

Unexpected, I was waiting for them to maintain a zig fork

Absolutely trash aftermarket batteries that are e-waste in 6 months here we come!