It's also relying on the assumption that the checking LLM only ever corrects wrong statements and never incorrectly "corrects" an already correct statement, which might not always be the case as well.

It's not thinking. Not in the way she probably meant. It can "think" that fast the same way a calculator can "think" that fast (kind of).

Because it's not human and not "thinking", it's a mathematical algorithm

I know.

If they already require your constant supervision the reason is money.

I just wish it wouldn't ask me to pipe an install script directly to shell to install.

Yes, I can probably inspect that but I do think installing through package managers is the best practice.

It looks better than pi with XDG and not being JS but that is it's own red flag for me.

I personally also don't like this, so use cargo to install it, it's in the readme. Takes a reasonable time to build on my X220, but on a modern computer it is plenty fast.

  cargo install --locked --git https://github.com/tontinton/maki.git maki

Is there a meaningful security difference between curl-pipe-bash and cargo install --git? Couldn't the cargo install include a buildscript that jumps right into a shell?

Sure, but you can review the git repo's content/commits in plain text, while curl-pipe-bash would require you to reverse engineer the binary that's downloaded.

If somebody hacks the project's home page and switches the download location to a hacked binary, you'd be none the wiser. Of course, somebody could hack the repo and add a deliberate vulnerability as well, but at least you would have a trail of it.

You can review the contents of the git repo before building it.

For curl | bash, you cannot. “But you can pipe to a fil—“ nope: https://tferdinand.net/en/why-curl-bash-is-a-dangerous-bad-h...

I've absolutely had the same experience. Pi has been praised a lot, people speaking so highly of it's code quality.

And then I installed it and found all the problems you mention. Not only that but I read Github Issues about the XDG problem and was a bit taken aback by the reaction of the developer.

It's one of the best agents I have used so far but I'm still looking for a very lightweight, token efficient agent NOT written in a JS framework and which respects XDG

I don't think that example applies at all here. The quote you quoted itself said it - "subjects for high art". Theres a difference between treating the banalities of life as SUBJECTS for your art and making human, non-mass produced art from that ( like the paining you linked) vs just treating the soup cans themselves as art.

At least that's my interpretation of it

I agree it's not a perfect parallel. But it was very much part of a movement that challenged traditional notions of what art was, and spurned similar debates and outrage as here.

Perhaps a more apt example would be Duchamp's "Fountain" (https://en.wikipedia.org/wiki/Fountain_(Duchamp))

No, Open weights US models would not break as well - this isn't related to China or USA, it's about Open Weights and the fact that you can download the models.

I've heard amazing things about pi and it's effectivenes but when I tried installing it I quickly found out it doesn't respect XDG_BASE_DIRECTORY at all, you need to set some environment variables and the author rejected both a proposal as "going full gpt", seemingly not even knowing about XDG_BASE_DIRECTORY, and even rejected a PR.

I've heard really good things but that being my first experience with pi didn't fill me with confidence about it's code quality either.

For now I stay with OpenCode I think - I was using zed editor and agent for the longest time anyway and think I will go back to that. CLI tools for me seem a bit too disconnected from the code.

Interesting! I wouldn't know, because I'm on mac. I love that it's very basic and I can basically do plug and play with the stuff I need. The load, complexity and system prompt overhang is quite minimal. But in the end, opencode is also fine I guess. I don't need to fiddle around with it too much and just need it to work. So if you're happy, why switch ;) I actually use zed as an editor w/o agents lol

GLM 5.2 is monstrous in size, no one is running that on their own hardware.

But it's a very competitively priced model other providers can offer (since it's open) so it's a much cheaper alternative than claude in practice.

I assume that is what they meant.

It's a bit of an indicator about the effort they put into it. If they don't even write their blogpost themselves the question of "how much effort and thought did they put into the rest of their code / product".

Now, obviously they might just be bad at writing blogposts but surprisingly often it seems to be a decent red flag.

Because the thing is that the less effort you put into that the more anyone can just...reproduce the idea with their own LLM.

Even if s.o buil a cool thing and wants to share it with the world, if all they did was prompt Claude for a weekend what is stopping me from just doing it myself? Then I can even get it however I want.

Or the time they had available. Maybe they have a full time job, parents to care for, kids to care for. But still they wanted to scratch the itch.

If someone has the time and opportunity to create a robot vacuum from scratch, they probably also have the time to write a short introduction for it

I disagree. Writing became seriously unfun after the 8th year of school. Now after grad school it seems very wasteful to spend any calories focusing on the packaging of the ideas and things. Especially at a time when we have achieved the technology to not need a team of writers, editors, and typesetters to create presentations of a worthwhile quality for the actual content in a reasonable timeframe.

It's never taken "a team of writers, editors and typesetters" to write a README.