techscruggs

Why wouldn't I just point claude at the interaction on your site and tell it to replicate it?

Agreed. The implication is, get really good at defining acceptance criterion.

Everyone would just programmatically filter out the ads.

Everyday, we get one step closer to the year of the Linux desktop.

>Feel free to then talk to them at length about all the reasons why AI, especially over-reliance on it, is bad for our society, like how it discourages learning, poisons the internet, angers everyone who is involuntarily subjected to it, and destroys our planet. Tell them that AI is not the future, but a creepy dystopia that this project wants nothing to do with.

I know that open source projects have struggled with the onslaught of AI slop. If I thought that was the motivation, I'd get it.

But that is so clearly not what is going on here.

thats not a suggestion.

I like Orca

Deepseek was cheaper, but also less accurate. "Beats" isn't a fair assessment.

This article seems incredibly biased. Is there a more balanced report of what is actually occurring?

I was a hardcore tailwind user and my projects still use it. That said, in the last 6 months, I haven't touched it. I just let my agents style things as they want. ... and they just use plain CSS.

I really appreciated tailwind, but it solved problems that fewer people face these days.

I never really understood what being "triggered" was like until now.

This is the type of security and vulnerability testing that actually matters. In a sea of security researcher noise, thank you for contributing in a meaningful way.

The challenge with this is that it often causes a proliferation of MCP tools which bloats context, which is one of the reasons that MCP was created.

I get your point, but it kind of is AI related. The size of PRs since AI has made it much harder to review a diff. Stacking the PRs seems like a response to this problem.

This sounds like exactly the kind of thing that some with a small penis would say ...