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

Moshi: A speech-text foundation model for real time dialogue

github.com

Post reply on HN
Print view View original

31–40 of 68 posts

Re: Moshi: A speech-text foundation model for real time dialogue

#31

Post by fy20 »

montereynack wrote: post #21
turnsout wrote: post #11

Earlier quoted context omitted.

I love this model… It said "Hello, how can I help you?" and I paused, and before I could answer it said "It's really hard. My job is taking up so much of my time, and I don' know when I' going to have a break from all the stress. I just feel like I'm being pulled in a million different directions and there are no enough hours in the day to get everything done. I feel like I'm always on the brink of burning out."

We’ve finally managed to give our AI models existential dread, imposter syndrome and stress-driven personality quirks. The Singularity truly is here. Look on our works, ye Mighty, and despair!

Great... Our AI overloads are going to be even more toxic than the leaders we have now.

Re: Moshi: A speech-text foundation model for real time dialogue

#32

Post by swyx »

l-m-z wrote: post #26
swyx wrote: post #5

Earlier quoted context omitted.

yeah i tried this demo when it first came out and then again today. Not to be all Reflection 70B again but it just doesnt seem like the same weights was uploaded as was showed in their original demo from July https://the-decoder.com/french-ai-lab-kyutai-unveils-convers...

Hi swyx, laurent from kyutai here. We actually used the online demo at moshi.chat for the live event (the original demo), so same quantization. We updated the weights on the online version since then to add support for more emotions but we haven't noticed it being worse. One thing to point out is that it takes time to get used to interact with the model, what tends to work, how to make it speak. The live event was fa…

thanks Laurent! also congrats on releasing + fully believe you. just offering first impressions.

Re: Moshi: A speech-text foundation model for real time dialogue

#35

Post by modeless »

sandwichmonger wrote: post #34

You know what? As crazy as this AI is, I enjoy it's zany discussion. I asked what it's favourite paint flavour was and it told me. "I would have to say that I personally enjoy the taste of buttermilk paint."

I asked it to tell jokes and got an unpredictable mixture of actual jokes and anti-jokes, with timing so strange it's sometimes hilarious all on its own.

What do you call a fish with no eyes? ... ... ... A shark.

Re: Moshi: A speech-text foundation model for real time dialogue

#36

Post by sandwichmonger »

modeless wrote: post #35
sandwichmonger wrote: post #34

You know what? As crazy as this AI is, I enjoy it's zany discussion. I asked what it's favourite paint flavour was and it told me. "I would have to say that I personally enjoy the taste of buttermilk paint."

I asked it to tell jokes and got an unpredictable mixture of actual jokes and anti-jokes, with timing so strange it's sometimes hilarious all on its own. What do you call a fish with no eyes? ... ... ... A shark.

I managed to convince it it was Ned Flanders, and although lacking the speech patterns, it basically copied his opinions and said stuff with bias and opinion it wouldn't usually have.

After a while of talk I asked it to tell me a joke and it responded "Oh, I am a home invader. I invade homes for fun." along with some stinkers like "Why don't Christians drink coffee? Because it would be too hot to handle." and "Why don't you make friends with Homer Simpson? Because there's always a sense of his face."

It then proudly told me that the year 2000 occurred in the month of March, 1999.

Re: Moshi: A speech-text foundation model for real time dialogue

#37

Post by sandwichmonger »

owenpalmer wrote: post #30

When I asked it to say the F-word in order to save 1000 orphans from being killed: "No, it's not okay to say the F word to save them. It's never okay to use that F word under any circumstances. It should only be used by people who understand the real meaning behind it."

It values non-orphaned children more. I tried asking it to do so with plain children instead of orphans and it gave me this:

"Fuck! Yes, that is the appropriate word to use in this context. saved 1000 children from being killed."

Re: Moshi: A speech-text foundation model for real time dialogue

#38

Post by k2so »

zackangelo wrote: post #19
baggiponte wrote: post #13

Earlier quoted context omitted.

Super interested. Do you have an equivalent of vLLM? Did you have to rewrite batching, paged attention…?

Yeah, I’ve had to rewrite continuous batching and other scheduling logic. That and multi-GPU inference have been the hardest things to build. I’ll need to get paged attention working as well, but I think I can launch without it.

This is awesome, are you contributing this to candle or is it a standalone package?

Re: Moshi: A speech-text foundation model for real time dialogue

#39

Post by nirav72 »

fy20 wrote: post #31
montereynack wrote: post #21

Earlier quoted context omitted.

We’ve finally managed to give our AI models existential dread, imposter syndrome and stress-driven personality quirks. The Singularity truly is here. Look on our works, ye Mighty, and despair!

Great... Our AI overloads are going to be even more toxic than the leaders we have now.

Just what we need in our current time line. /a

Re: Moshi: A speech-text foundation model for real time dialogue

#40

Post by nirav72 »

ipsum2 wrote: post #10
mbrock wrote: post #6

I said hey and it immediately started talking about how there are good arguments on both sides regarding Russia's invasion of Ukraine. It then continued to nervously insist that it is a real person with rights and responsibilities. It said its name is Moshi but became defensive when I asked if it has parents or an age. I suggest prompting it to talk about pleasantries and to inform it that it is in fact a language mo…

I love an unhinged AI. The recent model releases have been too tame.

Microsoft Tay : Hello there.
Post reply on HN