For web apps, explictly asking the agent to build in sensible checkpoints and validate at the checkpoint using Playwright has been very successful for me so far. It prevents the agent from strating off course and struggling to find its way back. That and always using plan mode first, and reviewing the plan for evidence of sensible checkpoints. /opusplan to save tokens!
> I still needed background jobs, real-time updates, and two-way communication that just works. Those things are possible in Rails and Laravel, but they take a bit more effort to set up.
These all have first class support in Laravel out the box.
I thought about it for a minute. I came to the conclusion that OpenAI would have likely tanked (perhaps even within days) had Altman not returned to maintain the status quo, and engineers didn't want to be out of work and left with worthless stock.
Is "Semantic CSS" just... CSS? There's no such thing as "Semantic CSS". There is Semantic HTML. I suppose there is CSS for Semantic HTML.
I've read the article and can't figure out if this is comparing the CSS framework Semantic UI to Tailwind?
If we're comparing CSS to a CSS framework, it seems fairly obvious to me that it's going to be bigger in size, and slower to load, and that the amount of code required to be generic (rather than totally specific) would be larger too.
It's not "easy" to find mutton in the UK either. My definition of easy (as for the vast majority of the population) is "is it in the supermarket". I don't think I've _ever_ seen mutton in a major UK supermarket. It's somewhat of a catch-22, but the supermarkets don't stock it because there is no demand (modern palates prefer less "gamey" flavours), and there's no demand because it isn't stocked.
Er, what? Yorkshire is famous for its lamb. Especially the Dales. And seafood - Yorkshire has some of the most bountiful coastline in the UK (e.g. crab).
This is an extremely odd way of making technology choices - especially the arbitrary 5 year limit that means having to use an older version of a framework.
> There were many quality of life improvements between Elixir 1.7 of 2018 and the Elixir 1.15 of today, but for most of our application coding these would make little to no difference.