The very features of AI that are exciting are also the reason why it is so intrusive to our privacy and security.
The very features of AI that are exciting are also the reason why it is so intrusive to our privacy and security.
Vocal minority of users was hostile to the idea of integrating so the developer switched to a separate plugin model.
Security theatre imho but understandable in some enterprises
The classic example is making everyone at US airports take off their shoes, have their shoes x-rayed, and then putting them back on -- for decades after the single incident in which a man failed to blow up a plane with explosives in his shoes. https://en.wikipedia.org/wiki/Richard_Reid
Moving code out into an optional plugin -- so that it can be verified not to be in use or even removed -- is not theatre.
Also, how exactly is the functionality going to run without manually adding the API key?
Its code to invoke a request to an API. where exactly is the attack surface? It’s not running an endpoint.
Finally, it’s a terminal app. It has access to way more powerful and sensitive tools with higher security risk
To be more accurate I guess i could have said privacy theatre but i think the point stands.
AI doesn't need to be anywhere near the Terminal without explicit intervention from the user, and I'm glad it's now in an external plugin.