unsloppable

Can someone save me a click? Does this improve quality or worsen it?

Tokens are cheap. Quality is what matters.

It helps if you've already got a decent codebase built in it with standard patterns covered.

Most of my sites start as a copy of an existing site as if it's a framework and then I clear out the product and just use the shell to build from. The result is that the agent is pretty good at replicating existing patterns and if I ever hit something similar I can just tell it to look up prior art in other projects.

The initial learning curve was definitely there, and I still hit edge cases as mentioned above. I just don't have to resolve the "how do I handle auth + middlewre + htmx targeting for a form in an admin screen (for a random example).

I am still 95% sure async/await was a mistake.

Async JavaScript using callbacks had a learning curve, but once you learned how to contain it and treat callback indentation as an opportunity to refactor it felt similar to coding in lisp.

The problem was the learning curve, and the fact you had to rewire your brain a bit compared to coding in something procedural.

HTMX is interesting.

I have most of my apps in it without much trouble.

One of my recent ones had a very complicated form and state management.

AI really struggled with HTMX in that use case.

Like the form might work but the page would take 30s to load. Or some state would randomly drop or a toggle wouldn't work after changing a dependency.

If I rewrote that in react it would have one shot it without a doubt. Some things are just better models for different problems.

For the record I eventually got enough tests in place to keep the agent honest and the HTMX version is now a lot faster anything I could have got out of react but yeah, it was an adventure.

I'm at the point I don't care. China models that propagandize openly is better than closed models that censor and restrict innovation.

If open AI wants to be taken seriously it needs to live up to its name.

Anthropic won't ever change.

I was waiting for them to explain what any of the real benefits were.

You cant figure out how those kinds of requirements might influence or curtail development in the non touch parts of the system?

We saw the same thing happen with mobile first on websites.

The trick is to render a larger frame in lower fidelity and then only render a smaller output frame in full fidelity.

Or render a low fidelity 3d model for coherence and then raytrace that onto a 2d frame that is then rendered at higher fidelity.

They're snappier, that's about it.

I find the lack of privacy forward thinking from a company I pay a couple hundred a month to kind of atrocious. They're buying no loyalty.

I've been harping on about async review for so long now. Glad to see it finally becoming a thing. Code review as a gate doesn't work for remote teams or AI lead development.

You need to decouple it, but you dont need to remove it.

Keeping the backlog funnel full has been nearly a full ltime job for me for about 5 years now. Both pre and post AI. Once you get a team together that knows how to execute keeping the backlog full of well defined and groomed tasks becomes the problem management rarely sees and subsequently doesn't know how to solve.

I built a tool for this due to having to read through huge amounts of AI generated text at work and actually comprehend it.

The text is AI models produce is incredibly dense and the way it structures sentences just makes long form reading excessively hard.

I basically wanted something that could expand copy into components of "meaning" and then dump the output back out in more normal language.

What I came up with is still "AI generated" but the readability is something passable.

Will definitely be taking a look through this and the recommendations.

I remember less than 1% of the code I ever wrote. AI hasn't changed anything for me.

Cool and clever.

One question: what do you use your old refs for?

We just delete them when we get too many.