this makes sense. preventing network access to it for a while would probably also work.  there shouldn't be any reason it's sending data out unless i explicitly ask for chatgpt help.

w3irdrobot

In my interactions with LLMs, copy-paste has been a useful step for thinking twice and doing sanity checks.

I'd only run this in a VM to start. Then I'd want to see and approve what's sent and received before execution.

With great power comes great responsibility.

OriginalSize

devs

apparently warp.dev is releasing their linux version in a few weeks. lots of AI stuff integrated into it that seem pretty cool. to those security/privacy minded out there and especially those who may have used warp already, what potential issues are there with having a terminal that is easily integrated with chatgpt?

note: i don't know a ton about how warp works. i don't know how often it sends data to chatgpt. so any information around that from existing users would also be welcome. 