ireadmevs

+1 to that. Offline is the only way I’d consider using a tech like that. And certainly not in a glasses form factor

Deterministic assurances on top of nondeterministic tools

> The entire source code, without tests, is about 15,000 lines, which comes out to about 150,000 tokens with GPT and about 250,000 with Claude.

Woah, that big of a difference when it comes to token counting?

If it’s just filesystem sandboxing that you are after, then bubblewrap can help you stay in nix by just wrapping the agent’s derivation

Try checking what M-x magit-toggle-verbose-refresh has to say, you may be able to identify what's slow and optimize around it

> the changes that end up in nixpkgs are all reviewed by maintainers

They review the “recipes”, sure. But I don’t know if I’d trust that every diff of the source of every package update is reviewed by them.

Really fun! Feels great when your hunch pays off, but most of the time it didn’t. I’ll be certainly playing it more often! Joining the share here:

Anthropeum.com · Jul 28 2026

YYBGYYRGGB

61,616 · top 66% of players today!

I guess there are 2 sides of ACP that are valid then. What was asked is for Juggler to act as a ACP client. I, on the other hand, would appreciate it to be a ACP server, so that I can interact with it from my editor when I’m on my machine and from the web when on the go or for more advanced functionality. That’s my current approach with opencode.

For me is the ability to maintain the same keyboard workflow, no matter if I’m dealing with files or terminal (switching buffers, navigating/searching/selecting/copying/pasting text, etc.), I get to keep the same set of shortcuts and mental model. And i get to do some small automation on top of it with elisp, which I already do for the rest of my editor anyway.

Yes, a link requires user interaction. But what if the attacker decides to render an image instead and put the secret data in the query params? Loading an image is a way to trigger a request without user interaction

I would even go one step further: why would an AI tasked with summarizing external comments require any tool access, especially being able to reach into non public data?

The solution to prompt injection is not more AI on top of it, it starts with data access controls

Thank you for sharing!

For public transportation I use an app called Moovit

Worth noting that nowadays nodejs std lib keeps growing and includes the aforementioned assertion and testing support.

https://nodejs.org/api/

Read Claude’s skill to create other skills and you’ll see that this ship has already sailed

https://skills.sh/anthropics/skills/skill-creator

I found it on the 2nd image! On the 1st one not yet...

And below everything else is the web version of MSOffice. How I hate whenever I’m forced to use that…

Whenever I know the name of the package I want to see, I always type in the URL directly: npm.im/[package-name]

How does the archive they provide look like? Many zip files? I would like to retrieve them and offload to another storage service but I don’t have local storage enough to hold all of it at the same time, unpack and then reupload. I would need to do it in stages.

There’s Tangled[0], but I don’t have personal experience with it.

[0]: https://tangled.org/

Well, just by reading the abstract I can’t tell if the results are positive or not. But glad to see more research being done on this area.

At work I use OneDriveGUI with no problems.

- https://github.com/bpozdena/OneDriveGUI

All of this is meant for 100% public data, right? Or is there a concept of visibility control? Can I create private communities, with data flowing just inside?

I’m always surprised when they (GPT 4.1 in my case) manage to get all of the closing parentheses right! I’d have guessed that having such a sequence of same characters would be a challenge for the LLM to use the right amount

It’s not that bad, you are still able to control your position and nudge the spawned enemies away, and force the boss to kill these enemies for you. And even if you get cornered here and there there’s plenty of time and space in this fight to heal back.

I do! And not only that, but I only read them through RSS.

Do you approve on every update of the package? Do they offer a way to quickly review what’s going to run and what has changed since the last approval? Otherwise it’s just like another checkbox of “I confirm I read the terms and conditions”

I haven’t the tried Hyprland, but I use i3, which I assume it should be similar. I do this sort of thing quite often when presenting on zoom at work. Suppose I want to present only the top-left section of my screen, then I split vertically first and the left side I split horizontally. This other 2 zones I use to put other supporting windows and to search stuff out of screen. When I need to present more apps, i3 also allow you to stack windows in a specific zone. It’s quite easy to switch between all the windows and have full control of the layout.

Not OP, but for me is the music plugin industry that almost never provides a linux VST. Some will work with wine, some won’t.

But for everything else I’m on linux as well.