Hacker News new | ask | show | jobs
by sangnoir 755 days ago
> What's your threat model?

Why do you ask, will you help with designing a mitigation plan?

I'll humor you: It's a turnkey gadget for sniffing/exfiltrating the output of any open iTerm2 shell.

1 comments

Because you’re already using other software that has LLM integration. What specifically about this iterm2 impl makes the threat more real??
> Because you’re already using other software that has LLM integration

Oh really, which software would that be? And which other LLM-enabled software connects production environments or has access to auth credentials/tokens?

How do you know what other software they are using?
Is someone not using GitHub these days? Or web search? Or macOS? Or Windows?
I use GitHub, I don't use its copilot.

I use web search, I don't use LLM websites.

I use MacOS, I don't use Siri.

I use Windows, I don't use Cortana/Copilot.

------------------------------------------

I don't want LLMs to parrot back code from other projects without understanding what that code does and what my code does. I don't want it to parrot back irrelevant slop.

And I especially don't want it to parrot:

rm -rf $BUILDDIR/ && ./build-project.sh

and just hallucinate the assumption that $BUILDDIR is already defined.

But GitHub doesn't ship copilot as a separate binary. So the threat vector of “AI has no place in my VCS get it out it increases the surface area” is there. So it’s okay for github to have copilot but not iterm2 to have codesierge? Doesn't add up.
Github isn't a binary, it's a repo host. Github can hallucinate whatever it wants, it's not going to brick my computer.

A terminal on the other hand...