This site is impossible to read on my phone. Part of the left side of the screen is cut off and I can’t scroll it into view
Show HN: Ask-human-mcp – zero-config human-in-loop hatch to stop hallucinations
11–20 of 65 posts
Re: Show HN: Ask-human-mcp – zero-config human-in-loop hatch to stop hallucinations
#12- someone sets up an “ask human as a service mcp” - demand quickly outstrips offer of humans willing to help bots - someone else hooks up AI to the “ask human saas” - we now have a full loop of machines asking machines
This is pretty much already possible in any economy, but quite a waste.
Not much is stopping you from buying products from a retailer and selling them at a wholesaler, but you'd lose money in doing so.
Re: Show HN: Ask-human-mcp – zero-config human-in-loop hatch to stop hallucinations
#13Re: Show HN: Ask-human-mcp – zero-config human-in-loop hatch to stop hallucinations
#14Cool conceptually, but how exactly does the agent know when it's unsure or stuck?
The same way it knows anything else. So not at all, but that doesn't mean it's not useful.
I'll try to give you credit for more than dismissing my question off-hand...
Yes, it may not need to know with perfect certainty when it's unsure or stuck, but even to meet a lower bar of usefulness, it'll need at least an approximate means of determining that its knowledge is inadequate. To purport to help with the hallucination problem requires no less.
To make the issue a bit more clear, here are some candidate components to a stuck() predicate:
- possibilities considered
- time taken
- tokens consumed/generated (vs expected? vs static limit? vs dynamic limit?)
If the unsure/stuck determination is defined via more qualitative prompting, what's the prompt? How well has it worked?
Re: Show HN: Ask-human-mcp – zero-config human-in-loop hatch to stop hallucinations
#15Earlier quoted context omitted.
The same way it knows anything else. So not at all, but that doesn't mean it's not useful.
I'll try to give you credit for more than dismissing my question off-hand... Yes, it may not need to know with perfect certainty when it's unsure or stuck, but even to meet a lower bar of usefulness, it'll need at least an approximate means of determining that its knowledge is inadequate. To purport to help with the hallucination problem requires no less. To make the issue a bit more clear, here are some candidate co…
I don't believe[1] any of those are part of the MCP protocol - it's essentially "the LLM decided to call it, with X arguments, and will interpret the results however it likes". It's an escape hatch for the LLM to use to do stuff like read a file, not a monitoring system that acts independently and has control over the LLM itself.
(But you could build one that does this, and ask the LLM to call it and give your MCP that data... when it feels like it)
So you'd be using this by telling the LLM to run it when it thinks it's stuck. Or needs human input.
1: I am not anything even approaching deeply knowledgeable about MCP, so please, someone correct me if I'm wrong! There do seem to be some bi-directional messaging abilities, e.g. notification, but to figure out thinking time / token use / etc you would need to have access to the infrastructure running the LLM, e.g. Cursor itself or something.
Re: Show HN: Ask-human-mcp – zero-config human-in-loop hatch to stop hallucinations
#16If you are answering these questions yourself, why not just add something like this to your cursor rules? "If you don't know the answer to a question and need the answer to continue, ask me before continuing" Will you have some other person answer the question?
I’ve tried putting “stop and ask for help” in prompts/rules and it seems like Cursor + Claude, up to 3.7, is highly aligned against asking for help.
Re: Show HN: Ask-human-mcp – zero-config human-in-loop hatch to stop hallucinations
#17This site is impossible to read on my phone. Part of the left side of the screen is cut off and I can’t scroll it into view
Same here
Re: Show HN: Ask-human-mcp – zero-config human-in-loop hatch to stop hallucinations
#18This site is impossible to read on my phone. Part of the left side of the screen is cut off and I can’t scroll it into view
Completely blank for me on mobile (javascript disabled)
Re: Show HN: Ask-human-mcp – zero-config human-in-loop hatch to stop hallucinations
#19This site is impossible to read on my phone. Part of the left side of the screen is cut off and I can’t scroll it into view
I also have this problem on my phone
Re: Show HN: Ask-human-mcp – zero-config human-in-loop hatch to stop hallucinations
#20If you are answering these questions yourself, why not just add something like this to your cursor rules? "If you don't know the answer to a question and need the answer to continue, ask me before continuing" Will you have some other person answer the question?
>If you are answering these questions yourself, why not just add something like this to your cursor rules?
What you are asking for is AGI. We still need human in the loop for now.