gitaarik

I have the feeling they do this to save tokens in case you didn't mean to execute such a big task right away. But yeah it's simple enough to say "Just do it now"

It makes sense that CC uses more tokens on bigger and complex code bases. And I'm happy it does; because of that it gets a good understanding of the architecture and how to properly solve the issue. And yeah for that you need at least a 5x plan.

Yeah or just use Ctrl + J

You can just use Ctrl + J

This is also the dealbreaker for me, I use copy / paste from the scrollback buffer all the time. And also quick search through the scrollback buffer. I don't want to first pipe all the output to an editor or pager or something; that messes with the terminal colors, indentation, and it's an extra step, making the whole process slower and more tedious.

But I guess Zellij people don't use the keyboard so much for copy pasting. A lot of people just use the mouse.

I don't know, when I started out as a web developer I met a hardcore C developer once and I was quite impressed about his low level knowledge, and wanted to eventually learn that too. But as time passed by the web world kept developping and becoming more interesting and eventually I want to make applications in the end. A few years later I saw the guy again and he told me he got into Ruby on Rails businesses, because there was a lot of work in there.

It's not that he just said it yesterday, he's apparently already said it a few times, and yesterday there was just a news article about it.

The Pull Requests were maybe manageable, but the backlog wasn't ;). AI does help with that. And the tools that require more stability you can still spend more time on and review the code.

Sounds very similar to my experience with colleagues before AI. It just goes even faster now.

I haven't heard of anyone that's using vibe coding to rewrite what they have. Most of what I hear is to create new things, and to accelerate development of existing projects.

> The Altman family has said Annie Altman has mental health challenges

I can imagine if you're been raped by your brother during childhood.

But of course now nobody will take her seriously because she has mental problems and Altman is a tech giant.

Not saying she's necessarily true. And you can probably never really find out the truth about this. But I think it's noticeable that there are these issues in their family. And not surprising that heavily traumatized children end up being narcissistic psychopaths.

Haha that's a good one!

So in this way we should dismiss all whistleblowers?

And you're comparing the DoD being hacked with the White House releasing a spy-app.

That is comparing incompetence with abuse.

It's both bad but different kinds of bad. One is ignorant, the other is evil.

So what's your point? Because previous administrations also make mistakes, we should accept all the crap coming from the current administration? That seems to be the only defense of the Trump fans these days.

Again, I agree that pervious admins were also crap, but that isn't an excuse for the current administration. We should be critical and sceptical regardless. And I think this current admin is actually worse, even so they tried so hard (or at least pretents) to fix everything. But it's all the same, left of right, they're all fooling us, and have us fighting among each other, so we don't see what's really happening behind the stage.

Don't domain registars auto-renew domains for you?

Come on, you're defending a sinking ship ;). Trump might be right about a lot of things, but that doesn't make him right about everything. And he and his whole administration pretends he is. And it's just pathetic and laughable how they try to keep denying how their decisions where maybe not always the wisest or most responsible. I think that is just very unprofessional, and just plainly simply childish. And I think it's becoming more and more clear that that is actually the way it is. The worse it gets the more they go in denial and the more they blame the woke democrats for everything that's their failures. They just don't know what responsibility is and only know how to turn around the narrative to blame others and to make it seem like they're the best ever. You just can't make this stuff up. But I'm actually enjoying it, because they're falling now and they're gonna fall hard. Interesting times.

It's only a mitigations if you already gave AI access. If you use it to for example generate some data based on research on specific data you gave it, you can feed back the AI the data to a human for human verification and then have the human have the final say. That's I think the flow we should use AI for mainly.

I agree that governments in general are very bad at this. But I also think that this admistration is even more special in it's own way.

As long as it doesn't auto-update it should be fine right? Just don't let those Aliens see that source code

Can't you delete your LinkedIn posts anymore after you posted them?

For an Android game downloaded from the Play store I wouldn't find these findings surprising at all. But from an official app from the White House? Well ok, from THIS White House - you're completely right to expect that.

Yeah it's great, we can actually let go of these silly open source projects like uBlock Origin, and just rely on the government for protecting us against the dangerous web!

True for any random game app in the Play store, and flashlight and note apps. But well reputable companies don't put too much weirdness into their apps.

Interesting argument, but I think statistics about video game addiction & mental problems etc was never really serious, and with social media it is.

Yeah people in the past were always more right. The people that built the first processors were much more aware of low level stuff than those so called low level programmers with their fancy compilers.

And before them, the electrical and mechanical engineers, without them we wouldn't even have these processors. We all ultimately are dependent on them.

And like that you can go on and on

Yeah there's no solution to prompt injection, but prompt injection in itself is not a security risk. It's about what you give the LLM access to. You can give it access to your complete DB and APIs, or you can only allow it to operate on a very specific piece of data.

If it's so little, why does Claude appear so prominently in the contributors section on GitHub?

Yeah good point. I think if the scraping code is written specifically for a site / system that prohibits scraping through it's ToS, the company has an edge for a lawsuit. It's a bit of a gray area I think. It depends how much of a threat you form to the company you're scraping, and how big the company is.

Interesting point. I've been looking into a similar issue recently, and for example LinkedIn won a lawsuit against the analytics company hiQ because they violated their ToS for scraping their website. And I think they also never technically had a direct contract they'd breach.

https://en.wikipedia.org/wiki/HiQ_Labs_v._LinkedIn