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

31–40 of 206 posts

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

#31

Post by pedalpete »

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 and confirm that our processes are being followed.

Any thoughts on if this might be a good solution? Or other suggestions by other HN users.

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

#32

Post by devmor »

This is the first new YC launch I've seen involving AI that I am extremely positive about. I have worked with systems implementing similar functionality ad-hoc already, but seeing it as a buy-in service - and one so easy to integrate - is really cool.

From what I've seen, this will bring the implementation needs for this kind of functionality down from "engineering team" to a single programmer.

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

#34

Post by cloudking »

Congrats on the launch, this is an interesting concept. It's somewhat akin to developers approving LLM generated code changes and pull requests. I feel much more comfortable with senior developers approving AI changes to our codebase, then letting loose an autonomous agent with no human oversight.

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

#35

Post by w-m »

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 become somewhat automated by the human, and the risky tasks won't be caught by the human anymore.

[0]: https://en.wikipedia.org/wiki/Automation_bias

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

#36

Post by chalkycrimp »

dhorthy wrote: post #25
chalkycrimp wrote: post #19

Startup owner using AI with this need - needless to say, a real problem. I've considered DIYing an internal service for this - even if we went with you we'd probably have an intern do a quick and dirty copy, which I rarely advocate for if I can offload to SAAS. I'm sure you've put a fair bit of work into this that goes well beyond the human interaction loop, but that's really all we need. Your entry price is steep (I…

thanks for the validation of the problem! totally open to feedback about the solution, and totally get that you only need something simple for now. I want to point out that we do have a pay-as-you-go tier which is $20 for 200 operations, and have a handful of indie devs finding this useful for back-office style automations. ALSO - something I think about a lot - if a all/most of the HumanLayer SaaS backend was open s…

My gut feeling is with where we're headed we'll clear that 200 pretty quickly in production cases, so we'd be interested in bit higher volume. Our dev efforts would probably clear that 200/mo. If the flow/backend was open-source that'd be a total game changer for us as I see it as an integral part of our product.

edit: I want to add here that while ycomb companies like yourself may have VC backing, a lot of us don't and do consider 500+/mo. base price on a service that is operations-limited to be a lot. You need to decide who your target audience is, I may not be in that audience for your SAAS pricing. This seems like a service that a lot of people need, but it also stands out to me as a service that will be copied at an extravagantly lower price. We have truly entered software as a commodity when I, a non-AI engineer, can whip up something like this in a week using serverless infra and $0.0001/1k tokens with gpt-o mini.

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

#37

Post by bravura »

There is definitely a need for this.

What I don't understand from quickly skimming your description and homepage: Do you source/provide the humans in the loop? That's a good value add, but how do I automatically / manually vet how you do the routing?

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

#40

Post by dhorthy »

bravura wrote: post #37

There is definitely a need for this. What I don't understand from quickly skimming your description and homepage: Do you source/provide the humans in the loop? That's a good value add, but how do I automatically / manually vet how you do the routing?

great comment - today we don't provide the humans, i think there's two angles here

- providing the humans can be super valuable, especially for low-context tasks like basic labeling

- depending on the task, using internal SMEs might yield better results (e.g. tuning/phrasing a drafted sales email)

Post reply on HN