tomgp

This is my experience too, it has got a bit better but nowhere near as quickly as other domains I deal with. I can usually guide the LLM to a decent solution but there's a lot of hand holding and I'm often left wondering if it wouldn't have been quicker for me to just get stuck in and do it the old fashioned way. Maybe because geospatial stuff is pretty niche so is under-represented in the training data relative to yr standard CRUD apps and React front ends which are ten-a-penny?

>But if it does, oh well. I'm glad our ancestors didn't take that line of reasoning we'd still be feudal serfs. "The lord has come and taken all our grain again? Oh well, at least I've been useful to him."

It seems people will never tire of finding out that writing code isn't the hard part of making useful software.

Even if you believe this surely it should be paid for by the employer not the individual.

I've played the campaign a few times now (10+) and my advice is 1. it's much better/ more manageable at 3 players unless everyone is already pretty experienced. 2. Try to play the first two acts in quick succession then the third maybe a week later once the dust has settled.

This has been my feeling in more optimistic moments for a few years, fingers crossed the adjustment isn't too brutal.

Think Flash (eventually) had most of these. That said, not all software development needs to happen at the same scale and not all software authoring environments benefit from the same tradeoffs vis-a-vis complexity, collaboration, accesibility etc. the success of Flash as a platform for independent game devs shows that different markets are better served by different tradeoffs.

Yeah, whilst I probably wouldn't go that far I take your point. I suppose the difference is in how people respond to the way games dress up their mechanisms and how interesting they find the decisions around the processes they perform.

I agree, they are just tools, but the way they are presented; taking natural language as their input and responding in kind strongly influences the way our brains react to them on a social level. That's what I mean by their social dimension.

The post has nothing to do with writing software. It would have as much value if it were written by someone who'd never written a line of code in their life. It's about the social dimension of LLMs and how the personality they present is, for some of us, pretty grating.

Martin is a good writer and (from what I've heard from those who've spent time with him) a lovely person which I think makes him well qualified to speak on the topic.

I'm really pleased for the devs and I like that they stuck to their guns and found their audience but...

as someone who decided to get on board at the start of this year I understand the negative comments. I'd really like to explore the universe and run a space station and whatever else but my 5 hours in the game were all schlepping round basically identical planets collecting different coloured stuff to convert into other different coloured stuff.

all of that said, Im glad NMS exists and that people get a lot out of it even though it's not for me. Hell, I prefer games that are divisive than something that's just blandly acceptable to the largest number of players like. alot of modern AAA titles.

I see where you're coming from but I don't think the analogy really works because most peoples experience of the internet is entirely 100% mediated by facebook, google, ticktok etc. It's would be like the road network if you needed to rely on a drunk driver to deliver you to your destination.

That's when the players are playing club football.

I think the issue is that the prose on the homepage gives off AI marketing BS "Everything you'd expect. Nothing you don't." "Native down to the pixels" etc. in an age where the web is stuffed full of low value llm generated content this is a strong negative signal for me (and i suspect others). No reflection on the app itself which I've yet to try but seems like a great idea