Hacker News

Completely blank for me on mobile (javascript disabled)

Switching to desktop mode fixed it for me

Rotate phone to landscape

Same here

I also have this problem on my phone

Finally, the "AI" turns out to be 700 Indians. We now have the full loop of humans asking machines asking humans pretending to be machines. Civilisation collapses

I built this - but mostly as a joke / proof-of-concept: https://github.com/olalonde/mcp-human

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.

reasoning models know when they are close to hallucinating because they are lacking context or understanding and know that they could solve this with a question.

this is a streamlined implementation of a interanlly scrapped together tool that i decided to open-source for people to either us or build off of.

Easy enough to do with smolagents and fastmcp, its 20 lines of code.

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.

Having another person answer the question is pretty much the obvious route this will go.

>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.

I had the same question reading your post:

> (problem description) your agent […] makes confident assumptions

> (solution description) when it’s unsure

I read this as a contradiction: in one sentence you describe the problem as an agent being confident while hallucinating and in the next phrase the solution is that the agent can ask you if it’s unsure.

You tool is interesting but you may consider rephrasing that part.

The same way it knows anything else.

So not at all, but that doesn't mean it's not useful.

the reasoning aspect of most llms these days knows when its unsure or stuck, you can get that from its thinking tokens. It will see this mcp and call it when its in that state. Though this could benefit from some rules file to use it, although cursor doesn't quite follow ask for help rules, hence making this.

The prompt is (mostly) built using the tool loads in the MCP server. In Python, the @mcp.tool() decorators provide the context of tool to the prompt, which is then submitted (I believe) with each call to the LLM.