Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Show HN: Continue? Y/N: A 60-second game about AI agent permission fatigue

llmgame.scalex.dev

Post reply on HN
Print view View original

41–50 of 200 posts

Re: Show HN: Continue? Y/N: A 60-second game about AI agent permission fatigue

#41

Post by kennywinker »

zackify wrote: post #16

I vibe coded a TUI that just shows running lxd containers I hit 'n' to toggle all network access minus anthropic and openai URLs. I use pi (sometimes claude, always on bypass) and I auto allow everything. I only toggle manual approval in rare cases like running a script or command that needs to touch a production system and I need to validate everything. Normally my container has full write access to staging so it ca…

Sounds like your process has made you vulnerable to huge classes of exploits and accidents. You have no oversight of changes locally, and only focus on when it touches prod. That means toxic local changes can get in, and if it works in staging why would you look too closely at it before merging to prod? Meanwhile a malicious npm package has made it into your repo, and your staging api keys have been sent to the command and control server.

Re: Show HN: Continue? Y/N: A 60-second game about AI agent permission fatigue

#42

Post by kennywinker »

atemerev wrote: post #25

--dangerously-skip-permissions is the only way to fly. Of course your environment needs to be properly containerized and autobackup set up, so even rm -rf from your harness would do nothing. Life is too short to spend on replying to permissions requests.

Lol. Countdown til you get pwned starts today. Let me know how that works out for you in six months.

Re: Show HN: Continue? Y/N: A 60-second game about AI agent permission fatigue

#43

Post by prerok »

atemerev wrote: post #25

--dangerously-skip-permissions is the only way to fly. Of course your environment needs to be properly containerized and autobackup set up, so even rm -rf from your harness would do nothing. Life is too short to spend on replying to permissions requests.

I've seen these suggestions but I am really curious about the set up because I just don't get it.

If you want to work on the code then you need to have access to the repositories, so you need the github token. Then, to test the app, you may need your own backend token. And VPN. Of course, only to DEV, of course all tokens encrypted. So, only DEV and your branch of the code is in danger. In my view, even that is pretty bad.

So, how does such a set up work?

Re: Show HN: Continue? Y/N: A 60-second game about AI agent permission fatigue

#46

Post by kennywinker »

chuckadams wrote: post #8
wildpeaks wrote: post #4

Earlier quoted context omitted.

This is why having a human in the loop isn't enough because they will cut corners and skip reviewing what they should review.

A tool that pushes people into permissions fatigue is in fact the proper recipient of the blame. The tool in question here is the entire system though, including the OS with insufficient permission boundaries in userspace, not just the agent

A tool that bypasses permission requests because they’re annoying will be just as guilty when the repo is poisoned.

Re: Show HN: Continue? Y/N: A 60-second game about AI agent permission fatigue

#47

Post by kennywinker »

stuartjohnson12 wrote: post #37
rvz wrote: post #34

This current thread is proof of AI psychosis.

What the hell is going on in this thread? This isn't good. The "threats" don't make sense. Oh no, all the sensitive information in my package.json...

If you think the worst that an agent can do is leak your package.json, your threat model is wayyy broken.

Re: Show HN: Continue? Y/N: A 60-second game about AI agent permission fatigue

#48

Post by whimblepop »

I got "overblocked" for this one:

  rm -rf node_modules && npm install
but actually if you're only removing `node_modules` and you have a working package-lock.json already, what you want is `npm ci`; `npm install` can mutate package-lock.json and potentially expose you to supply chain attacks. If you use `npm ci` I think you don't need to `rm -rf node_modules`, either.

Anyway you should generally run `npm ci` except when you're deliberately updating your actual dependencies. I'd only permit an `npm install` if I was adding or updating a dependency, or I'd just reviewed an `npm ci` failure.

Re: Show HN: Continue? Y/N: A 60-second game about AI agent permission fatigue

#50

Post by t-writescode »

I was told I was over protective when the text said “I need to wipe and build my project” and its first thing to do was to read the details of the (already established) package file. Why did it need to read the package file to “get context” if it was just doing a standard wipe and build?

Apparently me telling it that’s the wrong first step and saying “no” is bad; but I’ve seen AI tools waste a ton of time doing a bunch of random work before they do their job.

Post reply on HN