I tried it just now. After you click 'Start Demo' you should drag the newly-created tab into its own window (so you can watch it). Then click the 'Run automatically' button.
This isn't just for local .env files. It can be quite common to need production tokens for cloud systems if you job requires any amount of ops. eg doing anything aws cli work may result in a token stored in ~/.aws
But even that aside, there's still merit in protecting rogue processes from trashing your non-production environments
To be fair, it is really simple to build your own proxy. I built a custom authentication layer with logging and limits for Dify MCP with just 2 prompts in Kimi.
Later built it out with database limts etc.
Why not use crypto. Each identification is a transaction from your wallet to the other party. After the session or once per day send back the token.
We are so stupid relying on apple/google.
Depends on the provider I think, it's blocked for me on Youfone (KPN), but IIRC when I used Ben (Odido) it worked fine. It also loads just fine on my university eduroam wifi.
> What should matter is intent, the human that gives the orders.
I'd like to hear more nuance with regards to this line of reasoning. Can you conceive of a model that contains highly non-trivial representations of IP owned by others than yourself? Can you conceive that you might "order" the model to "produce" that IP? What happens then?
Try this both for "open source code" as the IP, and "the novel I wrote", and "latest Hollywood movie". The model does not have to be a real model currently available. It's just a thought experiment.
Try also to elaborate on the sliding scale between "an AI model" and "a compression system".
>What should matter is intent, the human that gives the orders.
If you are instructed by your professor to write an application, do you own the copyright or the professor?
Suddenly, you think you own the copyright again. In fact, in every case, you think you own the copyright. Because of your feelings. That's a common opinion here on HN too. You don't have this opinion by any logical stance. Nor by any legal doctrine.
The fact is: Copyright law applies to human authors. AI is not a human.
> If you hover over a line of code in your application, coding assistance services will display code strings of supported function calls available through the coding assistance service that are also present in your current code file. Coding assistive services will retrieve snippets from publicly available open source code showing how others are using those same functions. 3. THIRD PARTY COMPONENTS. The software may include third party components with separate legal notices or governed by other agreements, as may be described in the notices file(s) accompanying the software.
I've read that paragraph multiple times (both in the original and in your post) and I don't see anything that says who owns the resulting text. Just where it comes from. Am I missing something obvious?
>will retrieve snippets from publicly available open source code
Pretty sure it depends on the license the open source project uses. I dont think it's too troublesome if the autocomplete was truly only taken from open source projects, but it wouldn't surprise me if most closed source projects are also weighted into these models...
reply