You can use Cursor CLI, it's a terminal agent, just like Claude Code and Codex. I use it sometimes, I haven't opened the actual Cursor IDE in ages.
The potential benefit of Cursor CLI (vs CC and Codex) is that you can easily between all major models (by Anthropic, OpenAI, xAI, as well as Kimi K3 and GLM 5.2). I found it useful when reviewing work - e.g. I implement using Opus then review using Sol, etc. Models by different providers tend to have different perspective on things and they can find different issues with the code.
Zed lets you use Claude Code, Codex, OpenCode, etc. all through the same UI. Like you, I use that to cross validate using models from different providers and switch over to GLM 5.2 when I exceed my Claude Code limit.
Quite ironic. The original Robin Hood took from the rich and gave to the poor. Robinhood, the app, seems to do the exact opposite: it helps the rich get richer at the expense of regular folk.
This was always the Robin Hood play (versus being a grown up brokerage), they are simply griftmaxxing now in a "low regulatory environment". Like Coinbase, they need volume to succeed economically, not buy and hold investors. Crypto volume is down, so Coinbase revenue is down. Young people have little to no cashflow, but they have high intent to gamble in a crushing and financially nihilistic macro, which Robin Hood serves.
This should be limited to giving advice (education, warning, explicit consent), unless there's harm to third parties.
Because, you know, certain actions and even thoughts can lead to eternal damnation in Hell, according to what a society may think. Would you prefer the society to hold you off from that?
A child is not a fully autonomous person. I would of course take the loaded gun from the child, unload it, and explain its dangers to the child.
Money, in any form, may be as dangerous as a loaded gun, trading stocks or not. Most adults are careful with money, as they are with loaded guns. The problem is that some parties may try to make trading stocks (even leveraged) look much easier and safer than it is. It's like giving somebody a real loaded gun, while making it look like a toy gun, safe even for a child. And this of course needs to be regulated: not the trading, but the disclosure. This is not a toy.
Who are you to decide that a child is not a fully autonomous person? Sounds like you're imposing a normative rule based on societally derived presuppositions of right and wrong, which is exactly the point. We're just haggling over where the line should be drawn and you think it should be drawn somewhere further back than others do, but there's no truth to be found here.
> I ended up saying goodbye to those devops folks,
The irony is that "DevOps" was supposed to be a culture and a set of practices, not a job title. The tools that came with it (=Kubernetes) turned out to be so complex that most developers didn't want to deal with them and the DevOps became a siloed role that the movement was trying to eliminate.
That's why I have an ick when someone uses devops as a job title. Just say "System Admin" or "Infrastrcutre Engineer". Admit that you failed to eliminate the siloes.
Enabling Claude Code's sandbox (as OP suggested) does exactly that. It's a system-level filesystem sandbox that only permits access to specified locations for any process, including the python interpreter.
A profitable customer? How would Hetzner know if you're profitable or not?
I've hosted side projects on Hetzner for years and have never experienced anything like that. Do you have any references of projects to which it happened?
this! it favors established business with legal teams and (maybe more importantly) with connections.
The EU is also great at creating a heavy regulatory environment. Which entrenches existing incumbents. So the EU creates barriers that favor big companies, then tries to fix it with grants that... also favor big companies.
And then everyone's surprised that there's no innovation in Europe.
From all the world's companies worth over 100B$ there's only one European company - SAP, founded 50 years ago. [1]
>this! it favors established business with legal teams and (maybe more importantly) with connections.
This x2. A close friend of mine works at a major EU HW tech company and his job is wearing a suit, going to dinner parties and rubbing shoulders with high level local and national bureaucrats to convince them to fund X, Y, Z projects, none of which result in any major commercial success or ROI for the governments because the money they get is not enough to make new successful products, but hey, he's loving his job which gives him amazing job security against the waves of layoffs the company went through due to falling of sales, plus the networking he gets out of that is invaluable.
So at least some people are enjoying the gravy train while it lasts. But that's why a lot of EU tech companies immediately go to the US first before opening up to the EU market. US VSs are more generous with their cheque books than EU governments and investors, plus the 300 million people single consumer market speaking English as the common language and all that.
The comment you're replying to is tainted with the survivorship bias. We see successful companies that got government funding, but not the opposite. Maybe we'd have more innovation and competition without government picking these specific winners.
Ironically, one of the companies you mentioned (Apple) now operates in an environment with very little competition and regularly faces antitrust claims.
Government picking winners may actually reduce competition in the long run.
The key difference: when private money picks wrong, it's their loss. When government picks wrong, it's taxpayer money.
And in true google fashion, it only works with Google accounts; if you send a signature request to a non-google account, it says it's sent but does not work...
There’s a specific reason why google doesnt promote a Docusign like product even when they have superior technical abilities.
It probably comes down to the fact that code is not that crucial but all the other non technical aspects like distribution, supplier relations and marketing that makes a product.
Maybe LLM wrappers turn out to be that way. The model may not matter but the distribution and customer relation etc would matter more.
The potential benefit of Cursor CLI (vs CC and Codex) is that you can easily between all major models (by Anthropic, OpenAI, xAI, as well as Kimi K3 and GLM 5.2). I found it useful when reviewing work - e.g. I implement using Opus then review using Sol, etc. Models by different providers tend to have different perspective on things and they can find different issues with the code.