I tested Carter and holy, it is so real. Sometimes I think I'm talking with a person and it's impolite to look at another screen while chatting. It's very impressive that I have to tell Carter this 2 or 3 times lol.
carter's my new rubber duck
Show HN: A real time AI video agent with under 1 second of latency
181–190 of 264 posts
Re: Show HN: A real time AI video agent with under 1 second of latency
#182Is anyone else thinking that it might not be a good idea to give away your voice and face to a startup that is making digital clones of people?
Yea I start to load the chat and then was like wait a sec and noped out.
Same here. I was thinking maybe I'd give microphone permissions but didn't see why I had to show my video. Does the clone see my face? Maybe it does. That may creep me out more tho lol.
Re: Show HN: A real time AI video agent with under 1 second of latency
#183Earlier quoted context omitted.
> Always cuts me off. In my sci-fi novel, when characters speak with their home automation system, they always have to follow the same format: "Tau, , please." It's that "please" at the end that solves the stopped speaking problem. Am looking for alpha readers! (See profile for contact details.)
Honestly, that makes a lot of sense haha What's funny is that we even have a widely popularized version of this in the form of prowords[0] like "OVER" and "ROGER" [0] https://en.wikipedia.org/wiki/Procedure_word
Dang that just planted the visual in my head of talking to AI over walkie talkie. Not a bad interface. Push to talk, if it takes a few seconds or even a few minutes for a response to come back, not a big deal.
Re: Show HN: A real time AI video agent with under 1 second of latency
#184I had him be a Dungeon Master and start taking me through an adventure. Was very impressive and convincing (for the two minutes I was conversing), and the latency was really good. Felt very natural.
Hah- this is a great hackathon idea. I tried this concept just now and asked it (him?) to give a joke at the end. "What do you call an orc with two brain cells?... pregnant". Lol
Re: Show HN: A real time AI video agent with under 1 second of latency
#185Very cool! I think part of why this felt believable enough for me is the compressed / low-quality video presented in an interface we're all familiar with -- it helps gloss over visual artifacts that would otherwise set off alarm bells at higher resolution. Kinda reminds me of how Unreal Engine 5 / Unity 6 demos look really good at 1440p / 4k @ 40-60 fps on a decent monitor, but absolutely blast my brain into pieces a…
Ditto, we've actually seen this across the board with video. Even with real human recorded video. The 720p-ish resolutions consistently have the best results as they're the most relatable/natural.
Re: Show HN: A real time AI video agent with under 1 second of latency
#186Impressive demo. I’m working on the “brain” side of what I hope will back such real time agents. Any plans to provide hooks into these avatars so that i could potentially run my own logic?
You can already do this via the API! We let you peel back the layers and use your own LLM/logic, as well as other pieces of the pipeline (which we need to update the docs for)
Oh no. Now I want to see Dwight from The Office doing extremely terse code review!
Re: Show HN: A real time AI video agent with under 1 second of latency
#187Earlier quoted context omitted.
>Honestly this is the future of call centers. This feels like retro futurism, where we take old ideas and apply a futuristic twist. It feels much more likely that call centers will cease to be relevant, before this tech is ever integrated into them.
Tell that to my mom
Not to be macabre, but how old is your mom?
Re: Show HN: A real time AI video agent with under 1 second of latency
#188Earlier quoted context omitted.
> the kind of hackathon where people give up rights to any IP they produce Wow, I have been attending public hackathons for over a decade, and I have never heard of something like this. That would be an outrage!
This happens in corporate hackathons. Especially internal ones dreamed up by mid-to-upper management types who wished they worked at a startup. I had one employer years ago who did a 24 hour thing with a crappy prize. They invited employees to come and do their own idea or join a team, then grind with minimal sleep for a day straight. Starting on a Friday afternoon, of course, so a few hours were on the company dime…
I don't understand why most companies don't just run sensible, reliable, predictable processes like a Design Sprint when they're looking to break out of a local maximum.
Re: Show HN: A real time AI video agent with under 1 second of latency
#189Is anyone else thinking that it might not be a good idea to give away your voice and face to a startup that is making digital clones of people?
This is a valid concern, but we’ve always been very serious about consent and privacy. Our models cannot be used without explicit verbal/visual consent and you hold the keys to your clone.
> you hold the keys to your clone.
Can I run it on my computer?
If it doesn't run on my computer, what keys are you talking about? Cryptographic keys? It would be interesting to see an AI agent run on fully homomorphic encryption if the overhead weren't so huge - would stop cloud companies from having so many intimate, personal data of all sorts of people.
Re: Show HN: A real time AI video agent with under 1 second of latency
#190> This is hard. Basic solutions use time after silence to ‘determine’ when someone has stopped talking. But it adds latency. If you tune it to be too short, the AI agent will talk over you. Too long, and it’ll take a while to respond. The model had to be dedicated to accurately detecting end-of-turn based on conversation signals, and speculating on inputs to get a head start.
I spent time solving this exact problem at my last job. The best I got was getting a signal that thr conversion had ended down to ~200ms of latency through a very ugly hack.
I'm genuinely curious how others have solved this problem!