Treating the LLM as an untrusted execution thread at the OS level is probably the only sustainable way to handle agentic autonomy... Most frameworks try to manage permissions with application level logic which is basically just a game of whack a mole with prompt injection.
Don't trust AI agents
191–200 of 211 posts
Re: Don't trust AI agents
#192My assistant has no permissions at all and is just as useful. All it needs is todo, reminders and websearch (and maybe a browser but ymmv).
You are just some bad web searches away from being on suspect lists
For that reason I do have it on a vpn, doubt it'll ever happen since I don't see an attacker being able to prompt inject that easily opus in general won't do those kind of searches even if you jailbreak it, it will actually make the guardrails activate and will start refusing everything.
Re: Don't trust AI agents
#193My assistant has no permissions at all and is just as useful. All it needs is todo, reminders and websearch (and maybe a browser but ymmv).
> no permissions at all > and maybe a browser does not compute
A browser doesn't magically give access to secrets, it is useful for looking up things behind a captcha.
Re: Don't trust AI agents
#194My assistant has no permissions at all and is just as useful. All it needs is todo, reminders and websearch (and maybe a browser but ymmv).
> websearch (and maybe a browser Your assistant can literally be told what to do and how to hide it from you. I know security is not a word in slopware but as a high-level refresher - the web is where the threats are.
What will it do... leak my todo...? lol.
It's in a pod with zero permissions, secrets or access to the local network. It's also restarted daily incase somehow someone manages to escape a browser.
Re: Don't trust AI agents
#195[dead]
Re: Don't trust AI agents
#196Re: Don't trust AI agents
#197Earlier quoted context omitted.
Thank you for the time commitment based on an internet forum comment. I appreciate greatly the succinct human written README. Did you investigate prior art before setting out on this endeavor? https://www.google.com/search?q=site%3Agithub.com+password+m... I ask because engineers need to be clever and wise. Clever means being capable of turning an idea into code, either by writing it or recently by having the vocabul…
> Did you investigate prior art before setting out on this endeavor Lol no, I had no idea there was any other password managers! Thanks for the google search link! I didn't know search engines existed either! > Wisdom means knowing when and where to apply cleverness, and where not to. like being able to recognize existing sub-components. It says literally in the README that part of this is an exercise in seeing what…
If you didn't like me telling you about search engines you probably won't like me telling you how git clone works BUT...
For all intents and purposes, (in the context of diddling around with a password manager you might use yourself and wouldn't recommend to anyone), Any/all of those existing open source password managers can ALSO be yours just as much as the output from any LLM.
I'm serious, not only can you tweak them to "your tastes and your tastes alone", you don't have to even tell upstream maintainers what you're doing let alone get it merged.
Re: Don't trust AI agents
#198Earlier quoted context omitted.
> Did you investigate prior art before setting out on this endeavor Lol no, I had no idea there was any other password managers! Thanks for the google search link! I didn't know search engines existed either! > Wisdom means knowing when and where to apply cleverness, and where not to. like being able to recognize existing sub-components. It says literally in the README that part of this is an exercise in seeing what…
If you didn't like me telling you about search engines you probably won't like me telling you how git clone works BUT... For all intents and purposes, (in the context of diddling around with a password manager you might use yourself and wouldn't recommend to anyone), Any/all of those existing open source password managers can ALSO be yours just as much as the output from any LLM. I'm serious, not only can you tweak t…
So if you’re just going to complain about me reinventing the wheel (even though I already explained this is literally an exercise to see what an LLM can do), can we at least recognize the goalpost shift here?
I’m just going to assume that you’ve completely conceded your original point then, since you have absolutely zero to say about whether you agree the LLM did good work or not. Since the moment I showed you its work, you immediately shifted to insulting my intelligence for bothering with a password manager in the first place.
I honestly don’t know why I bother feeding trolls like you when it’s clear your only goal here is to find fault.
Re: Don't trust AI agents
#199[dead]
Re: Don't trust AI agents
#200Earlier quoted context omitted.
If you didn't like me telling you about search engines you probably won't like me telling you how git clone works BUT... For all intents and purposes, (in the context of diddling around with a password manager you might use yourself and wouldn't recommend to anyone), Any/all of those existing open source password managers can ALSO be yours just as much as the output from any LLM. I'm serious, not only can you tweak t…
So if you’re just going to complain about me reinventing the wheel (even though I already explained this is literally an exercise to see what an LLM can do ), can we at least recognize the goalpost shift here? I’m just going to assume that you’ve completely conceded your original point then, since you have absolutely zero to say about whether you agree the LLM did good work or not. Since the moment I showed you its w…
If we're talking about goalposts, lets also recognize the Motte and Bailey of initial claims of "20 years professional software engineer actually good password manager" to "hee hee toy project testing how LLms work not complete not even for personal not recmmond for others"
I don't think your password manager is good, and I don't think you think it's good either or you'd be using it.
I'm not trolling. It's way cheaper and faster to just clone an existing project if you want to mess around with making a password manager suit your taste.