Dunno, in work we wanted to implement a task runner that we could use to periodically queue tasks through a web UI - it would then spin up resources on AWS and track the progress and archive the results.

We looked at the existing solutions, and concluded that customizing them to meet all our requirements would be a giant effort.

Meanwhile I fed the requirement doc into Claude Sonnet, and with about 3 days of prompting and debugging we had a bespoke solution that did exactly what we needed.

the future is more custom software designed by ai, not less. alot of frameworks will disappear once you can build sophisticated systems yourself. people are missing this

That's a future with a _lot_ more bugs.

That's only if you do hands off vibe coding - I don't really use these models in reasoning mode - I'm still stuck at the 'smart autocomplete' stage, making it write funcion, web components etc.

I tried 'vibe coding' and I'm not the most expert AI coder, but the code it generated generally sucked - poorly structured, scalablity issue, the CSS was a mess with 3x as many tags as necessary with confusing and contradictory layout (that ended up not looking right).

I still don't feel like you can give the AI free rein, or you'll be in a world of pain.

youre assuming humans built it. also, a ton of complexity in software engineering is really due to having to fit a business domain into a string of interfaces in different libraries and technical infrastructure

What else is going to build it? Lions?

The only real complexity in software is describing it. There is no evidence that the tools are going to ever help with that. Maybe some kind of device attached directly to the brain that can sidestep the parts that get in the way, but that is assuming some part of the brain is more efficient than it seems through the pathways we experience it through. It could also be that the brain is just fatally flawed.

That's a future paid for by the effort of creating current frameworks, and it's a stagnant future where every "sophisticated system" is just re-hashing the last human frameworks ever created.

Bingo. LLMs are consuming data. They cannot generate new information, they can only give back what already exists or mangle it.

It is inevitable that they will degrade the total sum of information.