Just because you haven't seen it hallucinate on these tasks doesn't mean it can't.
When I'm deciding what tool to use, my question is "does this need AI?", not "could AI solve this?" There's plenty of cases where its hard to write a deterministic script to do something, but if there is a deterministic option, why would you choose something that might give you the wrong answer? It's also more expensive.
The jq script or other script that an LLM generates is way easier to spot check than the output if you ask it to transform the data directly, and you can reuse it.
> but if there is a deterministic option, why would you choose something that might give you the wrong answer?
Claude Code can use jq if it's installed on your system. Also, the data transformation is usually part of a larger workflow where an LLM is being used. And honestly, Claude is going to know jq better than 95% of developers who use it. jq can do a lot of things but it’s not the most intuitive tool to learn.
An obvious best practice is to have the LLM use existing tools to confirm the correctness of its output.
I'm a big fan of using this kind of thing at work. Rather than setting up a web server or packaging something into an installer, I just pop the bundled HTML file on a shared drive.
The CDN approach works, but I don't love depending on some third-party service just so your app continues working. Instead, I like using vite with vite-plugin-singlefile. This lets you package your JS and CSS into a single HTML: https://www.npmjs.com/package/vite-plugin-singlefile
I work in MUMPS daily and this is such an odd take to me. It's entirely possible to write very readable and maintainable MUMPS, and I find it fairly pleasant to write. There's lots of poorly written code, sure, but you can write bad software in any language.
This is really neat, I didn't know the browser would serve a page that had been generated by XSL. Is this just a hack, or is it an intended feature?
I notice, for example, that this doesn't include a <!DOCTYPE html> at the top, but it still functions because browsers accommodate incorrectly formatted HTML.
It's a feature! People used to build websites on this technology.
> I notice, for example, that this doesn't include a <!DOCTYPE html> at the top, but it still functions because browsers accommodate incorrectly formatted HTML.
When I'm deciding what tool to use, my question is "does this need AI?", not "could AI solve this?" There's plenty of cases where its hard to write a deterministic script to do something, but if there is a deterministic option, why would you choose something that might give you the wrong answer? It's also more expensive.
The jq script or other script that an LLM generates is way easier to spot check than the output if you ask it to transform the data directly, and you can reuse it.
reply