fleebee

It's worth noting that the Speculation Rules API and the View Transition API are not stable in Firefox and therefore aren't supported by all major browser.

The analogy is pretty generous towards LLMs. I like Eevee's response to it in her blog post[1]:

>What I do know is that a table saw quickly cuts straight lines. That is the thing it does. It doesn’t do Whatever. It doesn’t sometimes cut wavy lines and sometimes glue pieces together instead. It doesn’t roll some dice and guess what shape of cut you are statistically likely to want based on an extensive database of previous cuts. It cuts a straight f*cking line.

>If I were a carpenter, and my colleagues got really into this new thing where you just chuck 2×4s at a spinning whirling mass of blades until a chair comes out the other side… you know, I just might want to switch careers.

[1]: https://eev.ee/blog/2025/07/03/the-rise-of-whatever/

> There has been no shortage of evidence to support these claims.

One would usually show some kind of evidence after making such a statement. Claims from CEOs of AI companies don't count.

Considering the polarization, bubbles, misinformation and social isolation that social media has given us, I don't think we'd be any worse off moving back towards more intimate local communities.

It matters to me for so many reasons that I can't go over them all here. Maybe we have different priorities, and that's fine.

One reason why LLM generated text bothers me is because there's no conscious, coherent mind behind it. There's no communicative intent because language models are inherently incapable of it. When I read a blog post, I subconsciously create a mental model of the author, deduce what kind of common ground we might have and use this understanding to interpret the text. When I learn that an LLM generated a text I've read, that mental model shatters and I feel like I was lied to. It was just a machine pretending to be a human, and my time and attention could've been used to read something written by a living being.

I read blogs to learn about the thoughts of other humans. If I wanted to know what an LLM thought about the state of vibe coding, I could just ask one at any time.

The graphs don't line up. I'm inclined to believe they were hallucinated by an LLM and the author either didn't check them or didn't care.

Judging by the other comments this is clearly low-effort AI slop.

> LLMs have certainly damaged trust in general internet reading now, that's for sure.

I hate that this is what we have to deal with now.

I think you're late enough for that realization that the trend already shifted back a bit. Most frameworks I've dealt with can emit static generated sites, Next.js included. Astro feels like it's designed for that purpose from the ground up.

How often do we print debug something that isn't just a single variable? I have defined a macro in my editor that expands into a nicely formatted logger call when I type "dbg" and the variable name. I can do it without thinking or losing focus.

On the other hand, if I used an LLM to guess what I wanted to get logged (as the author did), I'd have to read and verify the LLMs output. That's cognitive overhead I normally wouldn't have.

Maybe I'm missing something, but I just don't find myself in situations where I only vaguely know what I want to debug and would benefit from an LLM guessing what that could be.

My job security is pretty low on my list of concerns about LLMs. I wish this technology existed only for vibe coding.

I worry about the impact of LLMs to the society at large. These models hit the mainstream only a couple years ago and they already have disastrous effects. Not only people send LLM generated emails to each other, that's actually a selling point for many products. I regularly hear about people using LLMs as doctors and therapists. For many, a chatbot could be their only friend or even a partner. Genuine human-to-human interaction is being replaced by chatbots from a handful of megacorporations. It's hard to avoid it. The internet is being flooded by LLM generated garbage that looks like a human could've written it. It's easier than ever to generate misinformation and propaganda, and as a cherry on top the LLMs even help distribute it.

I don't particularly want to live in a society where any of that's considered normal. And that's not even considering the negative impact on the environment. It's hard to be excited about a technology with these downsides that I think severely outweigh any benefits.

Thank you!

These are beautiful photos.

Would you consider adding an RSS feed to your website to help people keep up with it?

Where can I see the code?

Also:

> This wasn't something that existed; it wasn't regurgitating knowledge from Stackoverflow. It was inventing/creating something new.

Didn't he expressly ask the LLM to copy an established, documented library?

I tried the "thinking partner" approach for a while and for a moment I thought it worked well, but at some point the cracks started to show and I called the bluff. LLMs are extremely good at creating an illusion that they know things and are capable of reasoning, but they really don't do a good job of cultivating intellectual conversation.

I think it's dangerously easy to get misled when trying to prod LLMs for knowledge, especially if it's a field you're new to. If you were using a regular search engine, you could look at the source website to determine the trustworthiness of its contents, but LLMs don't have that. The output can really be whatever, and I don't agree it's necessarily that easy to catch the mistakes.

There's a number of good reasons not to make everyone run a kernel level anti-cheat. Linux (and therefore SteamOS) compatibility is a big one.

I think the status quo where anyone on any platform can access the vanilla game -- where cheaters may not even be a huge problem depending on one's skill rating -- and the most competitively-minded players have the choice to play on FACEIT, works pretty fine.

I do wonder what the 90% of built-in game content you're referring to actually is.

The animations on this website are disorienting to say the least. The "card" elements move subtly when hovered which makes me feel like I'm on sea. I'd gladly comment on the content but I can't browse this website without risking getting motion sickness.

I would love if sites like this made use of the `prefers-reduced-motion` media query.

You can go on walks with a cat without a leash. I do it every night. It's a bit different to walking a dog, sure, but he never strays too far from me. It might not be for everyone, but it works for us.

Not everyone has a deep understanding of LLMs or the self-control to avoid the temptation of off-loading thinking to one. Many people are desperate enough to look to LLMs for medical advice or even friendship[0]. As workplaces and schools partner with Big Tech[1], LLM interfaces have already become embedded in everyday life as something you can't ignore.

There are no guardrails to LLMs. They remove friction from tasks that used to require critical thinking. We're constantly pressured into using them. I think only blaming the end-user is naive.

[0]: https://aeon.co/essays/our-crisis-is-not-loneliness-but-huma...

[1]: https://www.forbes.com/sites/danfitzpatrick/2025/02/26/chatg...

Still, this kind of messaging pushes the fantasy that these LLM agents are intelligent and capable of scheming, making it seem like they are powerful independent actors that just need to be tamed to suit our needs. It's no coincidence that so many of the Big Tech CEOs are warning the general public of the dangers of AI. Framed that way, LLMs seem more capable than what they really are.

It's hard to take this article seriously between the unfounded claims and hyperboles.

It's not because of JS that semantic HTML and accessibility are neglected: it's because of inexperienced developers. If anything, modern libraries, frameworks and tooling empower developers to build modern UIs that are accessible. Of course, with power comes responsibility, but that's like blaming the car for speeding.

Wow. It's hard to believe this novella was written in 1909. The imagination and insight of the author is remarkable. It reads as an account of a dystopic future that we are now more and more living in the present.

Thank you for sharing this.

Different strokes for different folks, I guess. I hated that the UI was just rectangles in a grid with a single fill color. Few icons. The customization options were really poor from what I can remember, making it so that everyone's UI looked almost identical.

To be fair, I was getting seriously fed up by the poor software support at the same time which may have amplified my resentment.

Browser add-ons and/or userscripts may alleviate this problem if those are an option in your use case. I use Unhook (https://unhook.app/) to hide all algorithm recommendations and shorts.

That's a strange understanding of minimalism.