Agents that run while I sleep

python people don't update their libs, because then everything will break right and left. so they keep their security problems running.

And for what its worth, Typescript scaling, although better than PHP is still somewhat of an issue and If you want to have massive scaling, Elixir/ (to-an-extent gleam) are developed for solving the scalability problem especially with Phoenix framework in Elixir-land.

So I guess, jack_pp comment's about PHP can also be applied to an degree towards Typescript as well so we should all use elixir, and also within the TS framework the question can be asked for (sveltekit/solid vs next-js/react)

I am more on the svelte side of things but I see people who love react and same for those who love PHP. So my opinion is sort of that everyone can run in their own languages.

Golang is another language to be taken into consideration especially with Htmx/datastar-go/alpine.

How is this even possible? Am I the only SWE who feels like the easiest part of my job is writing code and this was never the main bottleneck to PR?

Before CC I'd probably spent around 20-30% of my day just writing code into an IE. That's now maybe 10% now. I'd probably also spend 20-30% of my day reading code and investigating issues, which is now maybe 10-15% of my day now using CC to help with investigation and explanations.

But there's a huge part of my day, perhaps the majority it, where I'm just thinking about technical requirements, trying to figure out the right data model & right architecture given those requirements, thinking about the UX, attending meetings, code reviews, QA, etc, etc, etc...

Are these people who are spitting out code literally doing nothing but writing code all day without any thought so now they're seeing 4-5x boosts in output?

For me it's probably made me 50% more efficient in about 40-50% of my work. So I'm probably only like 20-25% more efficient overall. And this assumes that the code I'm getting CC to produce is even comparable to my own, which in my experience it's not without significant effort which just erodes any productivity benefit from the production of code.

If your developers are raising 5x more PRs something is seriously wrong. I suspect that's only possible if they're not thinking through things and just getting CC to decide the requirements, come up with the architecture, decide on implementation details, write the code and test it. Presumably they're also not reviewing PRs, because if they were and there is this many PRs being raised then how does the team have time to spit out code all day using CC?

People who talk about 5x or 10x productivity boosts are either doing something wrong, or just building prototype. As someone who has worked in this industry for 20 years, I literally don't understand how what some people describe can even being happening in functional SWE teams building production software.

The cost concern is real but manageable. The key is routing models by task. Complex reasoning gets Opus, routine work gets Sonnet, mechanical tasks get Haiku. Not everything needs the expensive model.

The quality concern is the bigger one. What people miss about autonomous agents is that "running unsupervised" doesn't mean "running without guardrails." Each of my agents has explicit escalation rules, a security agent that audits the others, and a daily health report system that catches failures. The agents that work best are the ones with built-in disagreement, not the ones that just pass things through.

Wrote up the full architecture here if anyone's curious about the multi-agent coordination patterns: https://clelp.com/blog/how-we-built-8-agent-ai-team