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

201–206 of 206 posts

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

#201

Post by dhorthy »

ehsanu1 wrote: post #193
dhorthy wrote: post #167

Earlier quoted context omitted.

helpful - thanks! I have played with temporal a bit but have this thought that since most AI tools represent state as just a rolling context window, maybe you don't have to serialize and entire call stack and you can cut a bunch of corners. but we're all probably better off not investing that wheel

IMO just a rolling message history works for only the simplest of AI tools. Useful agents will tend towards much more complex state that extends into specific verticals/domains.

is that because of more deterministic AI flows like llm-as-judge, rag reranker, post-eval, etc?

do you think something like langgraph state is sufficient?

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

#202

Post by dhorthy »

usbsea wrote: post #187

10c per slack API call. I could make a mobile phone call for less than that in 1995. It is expensive... IFTTT, Zapier, NodeRed, etc. are your competitors. E.g. https://ifttt.com/applets/J75VtBA9-get-an-email-when-a-webho... -> https://ifttt.com/applets/KWqQedih-make-a-web-request-when-i... . They have lots of AI things too. The problem is you are saying "API" call so you are already dealing with devs. They can save $…

I think these are fair comparisons to make. I think the value is less in the slack api integration - anyone can plug in a slack client in afternoon.

When you get to timeouts, escalations, and routing 100+ conversations between 4+ users across multiple slack instances, that's when things got hectic for us.

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

#203

Post by j45 »

dhorthy wrote: post #159
j45 wrote: post #139

Earlier quoted context omitted.

First congrats on the launch - I like it. My feedback: what’s there looks inviting. Email interaction is handy, other ways would be too. If there was a low code way to arrange the humanlayer primitives for folks at the edge of using it, I think human tasks could meet something like this even broader. Happy to chat offline. Onto your comment: The coding for coding agents is still kinda prototype. It feels like some fo…

I think a lot about the low code side and how we can make that work...at the end of the day that looks like a feature/integration into other platforms and that means a lot of matching opinions/interfaces. I think K8s ecosystem did this well but it required big cross-enterprise working groups that produced things like CSI, SMI, OCI, and before that could happen, there was like 5+ years of storming and forming that had…

Maybe piggybacking on existing platforms is a way to go. You already have an API, maybe tying in a few major orchestration platforms like Zapier, n8n, make.com, and maybe even IFTTT, etc in one fell swoop would be a nice start to make it easier to tie in. Since you're into python, something like node-red might not be bad either.

There are lots of other process managers that could fit well with agents as well, python and not that could be reasonable bolt-ons or extensions.

I'd be very happy to check out the best agent orchestration architecture you're referring to, email is in my profile if easier :). 1

In terms of open sourcing, I don't think anyone would have an issue with .NET, I wouldn't. Many businesses have exposure to Microsoft 365 already and using Azure, kind of a massive built in audience.

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

#204

Post by dhorthy »

auxten wrote: post #184

I think Human Layer is a great idea. Recently, my baby turned one year old, which made me reflect on many issues. We train AI with a lot of data but overlook the impact that decades of seemingly useless data from human growth experiences have on our brain development. As a result, humans still have an incomparable advantage over LLMs in terms of the so-called "big picture." For example, a recent experience I had was…

interesting take - thanks for reading our story- here's to the future of human-aided-bash-novices not munging our PATHs up

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

#205

Post by 1f60c »

soheil wrote: post #93
1f60c wrote: post #45

Earlier quoted context omitted.

If you're talking about CAPTCHA solving as a service, that already exists, and the cost is measured in mere dollars per thousand CAPTCHAs solved.

Why the "if"? Of course, I was talking about captcha, is the regex parser in your brain case sensitive?

No need to resort to ad hominems; I just wasn't sure what you meant by "CAPTCHA as a use case" and wanted to point out that it's possible to do much better than $0.1/CAPTCHA solved.

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

#206

Post by endofreach »

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…

I have built a dumb internal service for this that i have been using for more than a year now. And just today i've thought about turning it into a simple product, as i am in need to finance the work on my actual product. Then i saw this Show HN & then your comment. Which makes me wonder: how would you use such a service "occasionally"? And what would be your pricing expectation?
Post reply on HN