How would a bunch of weights make a backdoor? The worst it could do is detect it's accessing an actual console and run a logged, visible command that tries to mess with your config or phone home, which is more of a front door with flashing lights saying "here I am!", so why would they bother?
Letting an LLM run arbitrary commands in your main user account seems risky even without worrying about conspiracies.
Just to wear my tin foil hat for fun, it's not that the model would attempt to phone home itself (what would it have to say, anyway?) but that given the opportunity it would go around kicking doors open for later infiltration by an outside party. Subtle bugs being introduced to your Django app, invisible characters that break your ssh configs, that sort of thing.
Yes, deliberately introducing vulnerabilities when generating code is a good one, and could be quite subtle. For running console commands though, anything touching configuration for ssh, gpg, bash aliases, ~/bin, cron, etc., should be immediately obvious.
I was thinking "here's an IP address and ssh key" would be what to phone home with, and that could be encrypted/hidden pretty well, but any network access should be pretty suspicious right away.
There is no backdoor but the model is heavily censored and biased towards China. It refuses to discuss Chinese or North Korean politicians, Tiananmen square, Uyghurs or anything sensitive to China. It's quite positive about Putin - it doesn't mind trashing Western leaders, though. It may write clever code, and I understand that Chinese researchers have to abide by local laws, but it certainly has opinions that are incompatible with mine.
given how Western models have their own biases, it occurs to me that we might be better off with a panel of models playing mock UN to cover everything.
We are now using S/mime and in today's Apple+Thunderbird products it's completely built-in and pain-free. Set it up once and after that all emails get encrypted automatically, you don't even need to press a button. Provided of course that You were able to convince your colleagues to invest those 10 minutes to set it up as well.
PGP Was painful because every Mail.app update broke it, not sure about the current state-of-the-art there. But the whole point should be: it is not much of an annoyance anymore! Zero annoyance after installation, Works even on your iPhone etc.
thinking that the Chinese government might have built in a back door gives me a little pause though