I don't know: we brand LLMs as "artificial intelligence", like it's the computer out of star trek.
On this website most of us know what an LLM is and how it works, but I could well see a young person asking it for advice and not knowing it could say the wrong thing.
They have a bunch of dumb react components that can become the gui for live targeting systems, but that all happens post contract and in the liability of their customers, the organizations willing to expend human capital coming and going, e.g. militaries
Fuel and food are excluded from core inflation not because they're unimportant (they are in fact incredibly important) but because they are much more volatile in price--going up and down in bigger increments--so that you get a more stable view of inflation by excluding them.
But it's a bit of a nasty trick because food, in particular, has inflated in price a lot the past 3 years. Some items, like sugar, are legitimately double the price they were.
Well - you converge to a system, but do that by pruning what you don't want.
If you care about maintainability and quality (and I include maintaining using LLM based tools) then you need to understand what it does (in doing so you will find lots of things for it to fix - you'll probably find that the architecture it's chosen is not right for what you want too).
Devs still have to maintain this code, the Python devs can definitely get the LLM to write (some kind of) Rust, but when it goes wrong and you hit the wall with the LLM then they can will have to learn Rust which might take a while, this sounds like a bit of a project risk.
A cynic would put this together with the plan to close all the NHSs source code: since the public wouldn't like further Palentir integration + be able to see it happening.
Overall using screentime as the metric, derived from some imperfect logging and vibes it's about 50% OpenCode 15% Continue 15% my homebrew bullshit 13% Claude Code and 7% Cline. I've been deep on agentic stuff lately (1.3wks aka 3 months of AI time), there are only so many hours in the day to duplicate work and AB test, but in the past I've sworn by Qwen Coder + llama.vim and I still enjoy that workflow for deep work far more than I like prompting agents, but there's a lot of dross I'm learning to delegate.
I stopped doing local stuff for a bit when I realised I didn't know how well it is supposed to work so have been on Claude for a few months now.
I think I'll try OpenCode this time.
Usually I do stuff in devcontainers, qwen code (non local) was the only time I managed to lose some work as it got confused when I ran out of tokens.
There's still quite a way to go - it does seem like Claude code itself is pretty badly coded, so I think there is a space for open source to come in with a high quality harness at some point.
reply