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

Launch HN: Human Layer (YC F24) – Human-in-the-Loop API for AI Systems

news.ycombinator.com

Post reply on HN
Print view View original

71–80 of 206 posts

Re: Launch HN: Human Layer (YC F24) – Human-in-the-Loop API for AI Systems

#71

Post by lunarcave »

dhorthy wrote: post #2

P.S. nobody asked but since you made it this far - the next big problem in this space is fast becoming, what else do we need to be able to build these "headless" or "outer loop" AI agents? Most frameworks do a bad job of handling any tool call that would be asynchronous or long running (imagine an agent calling a tool and having to hang for hours or days while waiting for a response from a human). Rewiring existing f…

The MCP[1] that was announced by Anthropic has a solution to this problem, and it's pretty good at handling this use case.

I've also been working on a solution to this problem via long-polling tools.

[1] https://github.com/modelcontextprotocol

Re: Launch HN: Human Layer (YC F24) – Human-in-the-Loop API for AI Systems

#73

Post by simplecto »

I knew this was coming, so kudos to you all for getting out of the gate!

I've implemented this in our workflows, albeit a bit more naive: when we kick off new processes the user is given the option to "put a human in the loop" -- at which point processing halts and a user/group is paged to review the content in flight, along with all the chains/calls.

The human can tweak the text if needed and the process continues.

Re: Launch HN: Human Layer (YC F24) – Human-in-the-Loop API for AI Systems

#74

Post by lunarcave »

pedalpete wrote: post #31

I'm considering this for a workflow agent and would be keen to hear thoughts on this process. We're a medical device company, so we need to do ISO13485 quality assurance processes on changes to software and hardware. I had already been thinking of using an LLM to help ensure we are surfacing all potential concerns and ensure they are addressed. Partly relying on the LLM, but really as a method to manage the workflow…

> manage the workflow

Hey, if you're specifically looking for providing deterministic guardrails around agent calls, I'm solving that particular problem.

We're sort of an "RPC layer for tools with reasoning built in", and we integrate with human layer at the tool level as well.

We're operating a bit under the radar until we open-source our offering, but I'm happy to chat.

Re: Launch HN: Human Layer (YC F24) – Human-in-the-Loop API for AI Systems

#76

Post by exhaze »

dhorthy wrote: post #64
w-m wrote: post #35

Interesting tool, congrats on the launch! I was wondering: have you thought about automation bias or automation complacency [0]? Sticking with the drop-tables example: if you have an agent that works quite well, the human in the loop will nearly always approve the task. The human will then learn over time that the agent "can be trusted", and will stop reviewing the pings carefully. Hitting the "approve" button will b…

this is fascinating and resonates with me on a deep level. I'm surprised I haven't stumbled across this yet. I think we have this problem with all AI systems, e.g. I have let cursor write wrong code from time to time and don't review it at the level I should...we need to solve that for every area of AI. Not a new problem but definitely about to get way more serious

This is something we frequently saw at Uber. I would say it's the same as there's already an established pattern for this for any sort of destructive action.

Intriguingly, it's rather similar to what we see with LLMs - you want to really activate the person's attention rather than have them go off on autopilot; in this case, probably have them type something quite distinct in order to confirm it, to turn their brain on. Of course, you likely want to figure out some mechanism/heuristics, perhaps by determining the cost of a mistake, and using that to set the proper level of approval scrutiny: light (just click), heavy (have to double confirm via some attention-activating user action).

Finally, a third approach would be to make the action undoable - like in many applications (Uber Eats, Gmail, etc.), you can do something but it defers doing it, giving you a chance to undo it. However, I think that causes people more stress, so it’s rather better to just not do that than to confirm and then have the option to undo. It’s better to be very deliberate about what’s a soft confirm and what’s a hard confirm, optimizing for the human in this case by providing them the right balance of high certainty and low stress.

Re: Launch HN: Human Layer (YC F24) – Human-in-the-Loop API for AI Systems

#77

Post by dhorthy »

conductr wrote: post #67
dhorthy wrote: post #55

Earlier quoted context omitted.

that makes sense - and have wondered a lot even more generally about the price of software and what makes a hard problem hard. Like Amjad from Replit said on a podcast recently "can anyone build 'the next salesforce' in a world where anyone can build their own salesforce with coding agents and serverless infra" I think in building this some of the things that folks decided they don't want to deal with is like, the st…

I’m just armchair quarterbacking here but I feel like you should just do all features for every user with a single $/action rate, then give discounts for volume and/or prepayment. Even saying $20/200 is a clunky statement. You could just say $0.10 per action (the fact that you’re actually requiring me to make a $20 payment with a $20 charge once it gets to $10 or something like that isn’t even important to me on a pr…

thanks - definitely worth saying - I've thought a bit about the 10c/operation rather than 200/$20 - might give that a shot or A/B test a little

Re: Launch HN: Human Layer (YC F24) – Human-in-the-Loop API for AI Systems

#78

Post by dhorthy »

simplecto wrote: post #73

I knew this was coming, so kudos to you all for getting out of the gate! I've implemented this in our workflows, albeit a bit more naive: when we kick off new processes the user is given the option to "put a human in the loop" -- at which point processing halts and a user/group is paged to review the content in flight, along with all the chains/calls. The human can tweak the text if needed and the process continues.

makes sense - glad to hear the problem resonates - if you had an extra engineer, how would you evolve what you have today?

Re: Launch HN: Human Layer (YC F24) – Human-in-the-Loop API for AI Systems

#79

Post by dhorthy »

SCUSKU wrote: post #66
david_shi wrote: post #47

We must do whatever we can to stay above the API: https://www.johnmacgaffey.com/blog/below-the-api/

Oh man, the API call for hl.human_as_tool() is a little ominous. Obviously approving a slack interaction is no big deal, but it does have a certain attitude towards humans that doesn't bode well for us...

so what I'm hearing is, if the approval is transparent and the agent doesn't see it, thats cool, but tell the agent "hey use the human as needed" and now we're getting into sci fi territory ?! either way i don't totally disagree

Re: Launch HN: Human Layer (YC F24) – Human-in-the-Loop API for AI Systems

#80

Post by ejp »

This is exciting. I am an architect in a startup that has long valued bringing humans in the loop for the moments when only humans can do the work. The key thing missing between the potential seen in the last couple years of LLM-based fervor and realizing actual value for us has been the notion of control and oversight. So instead, we have built workflows and manual processes in a custom way throughout the business. Happy to discuss privately sometime! (email in profile)

Congrats on the launch! I'll be thinking about this for a while to be sure.

P.S., there is a minor typo on the URL in your BIO.

Post reply on HN