gitaarik

If you haven't had this experience, I would rather think yóu are junior

But AI has actually enabled me to work through by backlog much faster, which decreases my chance on burnout.

And I still enjoy the process actually. It's a different process indeed. But times change, and you can't always do the same thing forever.

This asynchronous engineering progress has allowed me to do more householding in between. It maybe sounds crazy, but I feel it helps me organise my life better. For me it won't cause any burnout anyway.

They haven't only been trained on the common author. They have also been trained to prefer quality and to dismiss hallucinations. So if a human actually does some quality writing, people might think it's AI, like has already happened.

Yeah true, but I had many sites that I manually white-listed scripts / external resources, and was succesfully using those sites. But then some particular functionality of the site you rarely use once stops working, and you later find out uMatrix was still messing with some stuff, even if you whitelist all resources.

And what are you automating regarding your tmux sessions exactly actually? I use tmux daily, but I never feel the need to do any automation of managing my tmux panes.

The trial and chewing gum were designed specifically for dad's with no taste

Or you should wonder why they might jump instead of directly questioning their sanity. Then if you see the bridge is on fire and it's safe to jump into the water, then it makes sense, right?

But AI is trained on human text. Human writers have already been flagged as AI – by humans who think they're AI, while they were not.

How do YOU know?

I think what's important to make a good model is the quality of the information. Doesn't matter who made it, for what purpose, or how much money they made from it or are still making from it. It's just training data ultimately, and if it's useful data, we should incorporate it into the model, and if it's not, not.

The way people use the model is a different story; you can use it to do useful things, or you can use it to do harmful things. We should obviously have some regulation around that. That needs to be developed still I guess.

So there are no issues with unions in your view?

Of course it's not that black and white, but I don't think the previous commenter was necessarily painting it like that.

Like when Trump posts racist posts and then deletes it afterwards?

Yeah the 850 worded one is certainly AI, but I don't think it disproves the whole article. It's not an official study either, but things in between are allowed to be written about too.

Indeed, this is why I eventually stopped using it; sometimes a random site wouldn't function properly, and took time to figure out it was uMatrix. It was a nice plugin indeed though.

This is meant for people that are socially isolated, and don't have anyone to talk to about their personal issues and challenges. It's of course not great that it supposedly has a need to exists. But the fact that it is there to provide help to people that can't get it anywhere else, is a good thing I would think.

Edit: Apart from that, the people that are running it are probably not technically skilled or aware, so privacy issues like this should be highlighted.

Yeah indeed, you can move to a less popular ecosystem and have less risk. Back in the day when I moved from PHP ecosystem to Python, that was a big improvement. But with NPM I feel mixed; there's a lot of crap, but there's also genuinely good stuff. So you have to be a bit more conscious and alert when you make decisions on packages etc. With more mature ecosystems you have that problem less, and you don't have to spend so much time on package research and can rely more on the community. But still there's always a risk there too, so you have to stay alert.

I'm getting downvotes for this. Why exactly?

Yeah he's often not in a good mood, but at least he points out these things, and I understand it can get you worked up if you're investigating these things and come to these concerning discoveries. I'm happy someone is doing that work, even if it's not fun. And he seemed to have taken up that job, and I think he's doing it well, albeit he is sometimes a bit intense, but I would forgive him that.

Yeah, but to be honest, I sometimes just tell Claude to cleanup / refactor stuff; it finds a lot of things, discusses it with me and I approve the plan, and it churns away my tokens for some time. I do this once in a while, and I've been doing this for over 6 months and I don't feel like my development has significantly slowed down. Yeah my token usage is more for sure, but my codebase also is, so I'm not worried about that. To me AI seems to make maintenance very easy, like the rest. You just need to do it.

Edit: I make it sound a bit simple maybe. I do more extensive redactors also, where I'm more involved and opinionated. But I don't feel the need to do that very often very deeply. But yeah sometimes it's definitely necessary to prevent the project from going off rails.

Wasn't git invented for these kinds of things?

Isn't that like working on a codebase with an agent?

No, I don't know what you're doing if your agent is running for hours, but it sounds inefficient

You can however let them work in a sandboxed dev environment where if they break things it doesn't affect the productions system.

I don't think you should only let "if it sounds good" determine what you eat

Is coding without the "agentic" part any different from copy pasting code from the internet like a script kiddy?

Funny, for me Claude Code works perfectly, and I don't have to wait for hours, my prompts are usually done within minutes. And the results are most of the time great.

That you say that he will win again is kind of trolly, you want Trump for a 3rd presidency? You really want a dictator?

It is true that you can't easily point out many lies, he's indeed not lying all the time, and he is indeed not stupid, he knows very well how to talk. I must agree that I've also been surprised by his relative intelligence.

But I think ultimately he is a classic politician in the way that he has his own agendas and motivations that he doesn't talk about, but he knows very well how to frame it into a picture that sounds good for the public.

And I think he is actually exceptionally good at it, but also bad at it at the same time. Because yeah he hasn't been very seriously been openly caught for an obvious crime. Well.. apart from being convicted for covering up his sex scandal. But he knows how to persuade a lot of people. And he knows how to play the business game without being caught.

But people that look more closely and critically can see that not all actions add up to what he says, he keeps changing his mind and his talk, and other concerning movements are happening on the background, that when Trump is being confronted with, he goes into denial, defense and even attack.

Next to that, I think his attitude is unprofessional, unkind, unthoughtfull and often even offensive. And I think his attitude is driving an ongoing polarization in society. I feel he is rather dividing the country than uniting it.

Maybe you need to clean up MCP tools? My codebase is very large (hundreds of files, hundreds of lines per file), and I am managing fine on a 5x subscription, chatting all day.

Some time ago I cleaned up a bunch of MCP tools I had installed some time ago and that did make a significant impact on token usage.

But you also spend less time on those tasks, allowing you to do more of those tasks. And if you still spend the same amount of time, and use AI as am assistant, and do review the AI's work, then you can actually learn from it faster.

But I understand that many people don't do that and just finish their task with AI and then don't do anything anymore.