I don't really program with AI, as I find the code quality pretty poor.

I use Retool for all our internal tools. I like the fact that somebody else is looking after the hosting of the dozen little one-purpose applications I've built, and it all just works.

Ultimately I'm just after a quiet life.

In the UK tech hiring is fairly buoyant at the moment, and the salaries being offered have got some long-needed growth (over this last year we've begun seeing 6 figure senior developer jobs in the east midlands, whereas a couple of years ago getting a £60k salary for a senior in the east midlands was quite the achievement).

Woah the £100k glass (class) ceiling was broken in the east midlands? Does it involve commuting to London?

Fortunately it does not. I'm in Nottinghamshire, and the only way I used to be able to do £100k round here was contracting, but the times they are a changing it seems.

That's fantastic, especially in light of the death of IR35 contracting

Hmm, interesting, maybe I should look into the UK market then... Because I often see open positions in the UK segment on the company job boards, just didn't know if it's mostly fake ones as in NL and FR.

The ones I see coming up repeatedly on LinkedIn are real jobs, but for places with high staff churn - Bet365 in Stoke for instance have a voracious appetite for recruiting System Development Managers, mainly because they can't get anyone to stay in the role more than a month.

Last time I checked they don't pay well though.

Unlikely they'll hire people requiring visas though. Unless you're exceptional talent, of course.

They're still pretty dreadful. They're better than I was at 21, so I'd say they're good for graduate level, but nothing beyond that.

Which models + versions are you using? Can you give a specific problem that you found them to be bad at?

The most recent logic I tried getting it to code for me was to make me some recursive C# functions to reverse navigate a node map (a Microsoft Project plan with various feeding chains) to calculate all possible paths, and return them as a list of objects.

It kept producing code that looked to eye that it might work, but each time I ran it it would just throw schoolboy exceptions. I got tired of telling it to correct the things it kept forgetting to check for (nulls, path starts, empty lists), and just coded it from scratch myself.

I find ChatGpt is like pair-programming with a junior, except I'm not getting paid to coach them like I would if it were an actual graduate hire.

I think I'm doing just fine, thanks for your concern.

keeping context is a thing that they are bad at. For now, i admit, but they are.

Given a long haul goal with instructions and everything they will reinvent the wheel four times and one of those you will get a square. Reminds me of that monkey paw wish thing. You look at your finished app. Looks beautiful, but its inner workings are a ball of confusion.

Thanks ChatGpt.

No. My own words. But I'm taking some heat here for letting folks know my book is available. I thought Show HN was a place for that.

I've only recently begun using copilot auto-complete in Visual Studio using Claude (doing C# development/maintenance of three SaaS products). I've been a coder since 1999.

The suggestions are correct about 40% of the time, so I'm actually surprised when they're right, rather than becoming reliant on them. It saves me maybe 10 minutes a day.

The only part AI auto complete I found I really like is when I have a function call that takes like a dozen arguments, and the auto complete can just shove it all together for me. Such a nice little improvement.

My least favourite part of the auto complete is how wordy the comments it wants to create are. I never use the comments it suggests.

I have been begging Claude not to write comments at all since day 1 (it's in the docs, Claude.md, i say the words every session, etc) and it just insists anyway. Then it started deleting comments i wrote!

Fucking robot lol

I find it writes them like a boring neighbour who hasn't talked to anyone for a few days; it just seems to reiterate the same thing three times, worded slightly differently, but not adding anything extra with each sentence, like there's a word count it's aiming for.

Do you mean suggesting arguments to provide based on name/type context?

Yeah, it usually gets the required args right based on various pieces of context. It have a big variation though between extension. If the extension can't pull context from the entire project (or at least parts of it) it becomes almost useless.

IntelliJ platform (JetBrains IDEs) has this functionality out of the box without "AI" using regular code intelligence. If all your parameters are strings it may not work well I guess but if you're using types it works quite well IME.

Can't use JetBrains products at work. I also unfortunately do most of my coding at work in Python, which I think can confound things since not everything is typed

... you can't use JetBrains? What logic created a scenario where you can't use arguably the best range of cross platform IDEs, but you can somehow use spicy autocomplete to imitate some of their functionality, poorly?

I work in an extremely security minded industry. There are strict guidelines about what we can and can't use. JetBrains isn't excluded for technical reasons, but geopolitical ones.

The AI models we use are all internally hosted, and any software we use has to go through an extensive security review.

> JetBrains isn't excluded for technical reasons, but geopolitical ones.

This makes perfect sense. Who could possibly trust a company run from... the Netherlands.

I get that you don't make the rules you're working under, but Jetbrains of all companies seems like a bizarre "risk" factor, given their history and actions.

Quit your palantir job, spook.

Micro Men. British film about the beginnings of Spectrum and Acorn.

It's mostly been due to the code quality: everything LLMs have spat I've had to heavily edit to make it readable, good quality code, and that's when the code actually works - the number of iterations it takes me to get code that actually works normally means I could have coded it faster myself without trying to get an LLM to do it.

Defence. We don't use any LLMs, and couldn't even if we wanted to.

To be fair the code they produce is dogshit, so it isn't a problem.

That might be a good candidate, right.

I am baffled about how each company are jumping into LLMs without considering anything about their own privacy when 10 years ago, just using GitHub with a private repository could have been an issue.

> To be fair the code they produce is dogshit, so it isn't a problem.

That's not a problem for managers and CTO that are just being brainwashed by marketing and LinkedIn posts that all their engineers should use Cursor.

True. There's a bubble that will burst with LLM stuff, I am sure of it.

I'm on Vodafone, I can confirm they're okay.

I agree, but I still call myself a software engineer...