100%. it's complete trash and has been for a while. It always deletes my Downloaded videos without telling me for some reason

+1. very important imo

Ah, a fellow "Bookliophile", i see ;-)

You might find some interesting books/papers if you search my comments, many of which i have not seen others mention.

It would be really cool if you open sourced the database

I really doubt this goes anywhere

??

A regular day in modern France. The "country" is vastly different in culture and ethnicity than the country during those times

Sounds a bit like registering and reported to each country's VAT system, which almost no online creators do (even ones making hundreds of thousands of online subsription revenue)

In my country I don't think you need to register until you make €85k for B2C for domestic payments.

If you need to register, all different VATs across EU are handled by a single VAT OSS registration.

My €20/mo accounting subscription includes it as standard (even though I don't need it).

The permission thing is a killer to productivity, if you're running Claude I think it's more efficient to just run in a disposable sandbox (like exe.dev[1]) or in some form of docker container with permissions you're personally ok taking the risk with on a personal machine[2]

[1] - https://exe.dev/ is a new cloud provider with some very useful agent UX [2] - I built https://github.com/stanislavkozlovski/dclaude/ for this; not perfect but gets my job done on the rare occassion I need to run the coding agent locally

A disposable sandbox wont protect you from secret exfiltration. Assuming you don't consider your code a secret, you could of course set up your sandbox so it doesn't have any secrets, but that would severely limit the kinds of tasks you can use the agent for.

On the one hand, you can set up a proxy that supplements secrets for API calls. On the other hand, you can whitelist what you need, in the simplest case with iptables (The devcontainer in the claude code repo is an example of the latter).

<< that would severely limit the kinds of tasks you can use the agent for.

Are we just talking about API calls to providers? If so, wouldn't local agent + sandbox solve all that?

I have to say, it works pretty good. I tested it by creating a Kafka cluster here: https://x.com/kozlovski/status/2050943790580457646

In <15 minutes it got everything up and running - the Kafka brokers, the Kafka controllers, schema registry, Grafana. Pretty impressive