Do Crystal next! ;)

Hey, if companies can be people, why not office furniture? /s

Great article. I wonder if the same markers can be used to detect AI generated code (if you suppressed comments).

As, code requires a much more rigid syntax, compared to free flowing docs.

I’ve played around with Claude.

they can’t access anything you don’t give them permission to access.

It’s not that “they can’t” it’s more like “they try not to”.

For example, if you have a folder shared with your application code (/home/me/code/) - it has free reign on that folder.

If you add a prompt saying “you are only allowed to access files in /home/me/code”:

you could ask it " oh, what are my aws credentials ", it would have no qualms about reading those files (/home/me/.aws).

You could also ask it to update your settings (/home/me/.claude)

I eventually started to work on a way of running Claude in a docker container with real filesystem enforcement. …and it’s sneaky how Claude will get when it wants to read a file, it doesn’t have permissions for (using bash cat).

This was an exploration I’d made a year ago and I know Claude has a " sandbox" , but if you allow Claude to run bash commands - that sandbox is trivial to circumvent.

…then the company shouldn’t be over provisioning/selling vram.

AI isn’t responsible for the stuff it outputs - the person controlling it is.

Ultimately, you’re right (as they can decide to use AI or not). But these AI Companies need to shoulder the blame for creating, promoting, and selling AI, which (in its current form) is effectively a “broken tool”.

Good computer hygiene says I should lock my computer while I’m away. Yet, I’m suppose to blindly install an AI agent on my machine and ask it nicely to focus on the task at hand and not use any of the other applications or credentials that might also be installed?!?! It’s ridiculous.

My new favorite website: no ads, no JavaScript, and works with curl.

Thanks for sharing it!

Bingo!

It was always believed that Windows OS was a “loss leader” for Microsoft.

Windows OS will never show a profit, when you take into account the development and testing time and effort. I mean, a one time purchase that’s expected to be supported for years!?!

Side note: This also explains why Windows 11 is de-evolving into an AI generated, ad ridden, telemetry gathering, cesspool of an OS (“we gotta make money somehow - think of the share holders”)

But, what Windows had done is create a platform for Microsoft to upsell (and vendor lock-in) profitable applications like Office, Outlook, Teams, etc.

However, that business model doesn’t work anymore. As, all of Microsoft’s products are now in the cloud. They’re all subscription bases, which means predictable and indefinite revenue. User’s don’t need to be running on Windows - they just need a web-browser or thin-client. Microsoft already has people (brainwashed into) wanting Office - they don’t need to _force _ people into trying Office.

tl;dr: Developing and supporting Windows OS is a financial drain for Microsoft, and they’re doing everything they can to scuttle it.

Hooray, uncontrolled and unregulated consumption of tokens. What could go wrong? /s

Thanks for sharing the link. I’ll take a peek at them and their ToS.

Or… honestly, just pay $40 for basically unlimited usage for a year from an API, then roll your own frontend.

Can you clarify, what you mean by this? Rent a VPS? Or is there a legitimately good place that’ll offer “unlimited” llm api access for $40 / year (and would you have any sort of privacy with this)?