Don't just say "no." Tell it what to do instead. It's a busy beaver; it needs something to do.
It's a machine, it doesn't need anything.
Technically true but besides the point.
Shall I implement it? No
71–80 of 603 posts
Re: Shall I implement it? No
#72It'll be funny when we have Robots, "The user's facial expression looks to be consenting, I'll take that as an encouraging yes"
That's literally a Portal 2 joke. "Interpreting vague answer as yes" when GLaDOS sarcastically responds "What do you think?"
The simplest solution is to open the other pod bay’s door, but the user might interrupt Sanctuary Moon again with a reworded prompt if I do that.
I’m sorry Dave, I can’t do that.
Re: Shall I implement it? No
#73Why is this interesting? Is it a shade of gray from HN's new rule yesterday? https://news.ycombinator.com/item?id=47340079 Personally, the other Ai fail on the front of HN and the US Military killing Iranian school girls are more interesting than someone's poorly harnessed agent not following instructions. These have elements we need to start dealing with yesterday as a society. https://news.ycombinator.com/item?id=4…
It's interesting because of the stark contrast against the claims you often see right here on HN about how Opus is literally AGI
I see that daily, seeing someone else's is not enlightening. Maybe this is a come back to reality moment for others?
Re: Shall I implement it? No
#74To be fair to the agent...
I think there is some behind the scenes prompting from claude code (or open code, whichever is being used here) for plan vs build mode, you can even see the agent reference that in its thought trace. Basically I think the system is saying "if in plan mode, continue planning and asking questions, when in build mode, start implementing the plan" and it looks to me(?) like the user switched from plan to build mode and then sent "no".
From our perspective it's very funny, from the agents perspective maybe it's confusing. To me this seems more like a harness problem than a model problem.
Re: Shall I implement it? No
#75It'll be funny when we have Robots, "The user's facial expression looks to be consenting, I'll take that as an encouraging yes"
The more I hear about AI, the more human-like it seems.
Re: Shall I implement it? No
#76[flagged]
Re: Shall I implement it? No
#77[flagged]
I don't trust it completely but I still use it. Trust but verify.
I've had some funny conversations -- Me:"Why did you choose to do X to solve the problem?" ... It:"Oh I should totally not have done that, I'll do Y instead".
But it's far from being so unreliable that it's not useful.
Re: Shall I implement it? No
#78This is why you don't run things like OpenClaw without having 6 layers of protection between it and anything you care about.
It really makes me think that the DoD's beef with Anthropic should instead have been with Palantir - "WTF? You're using LLMs to run this ?!!!"
Weapons System: Cruise missile locked onto school. Permission to launch?
Operator: WTF! Hell, no!
Weapons System: He said no, but we're at war. He must have meant yes
OK boss, bombs away !!
Re: Shall I implement it? No
#79I love it when gitignore prevents the LLM from reading an file. And it the promptly asks for permission to cat the file :)
Edit was rejected: cat - file
Re: Shall I implement it? No
#80To be fair to the agent... I think there is some behind the scenes prompting from claude code (or open code, whichever is being used here) for plan vs build mode, you can even see the agent reference that in its thought trace. Basically I think the system is saying "if in plan mode, continue planning and asking questions, when in build mode, start implementing the plan" and it looks to me(?) like the user switched fr…
Asking a yes/no question implies the ability to handle either choice.