Sorry I'm lost. The sample on the homepage sounds absolutely awful. Not one bit of the cadence individually and together, the tonal ranges in responses or the overall structure and feel is comfortable to listen to, it's so far off passing as 'real' that I feel like I must be missing something.
>That doesn't sound like the same bar as "most authentic full-duplex speech model ever built"
It's up there. I think most humans would be convinced they're talking to a human. I assumed you've used other speech models. They are okay, but not as natural and imperfect as Dessa is.
I'm surprised it took this long! Clearly the next step is joint training on text and audio. The speech realism is very good, but the intelligence is pretty clearly 2024-level.
These bidi/duplex demos always come off as overly artificial to me. It's cool that the model can speak at the same time as you instead of taking turns, but training it to interrupt as much as possible isn't the way to do it. In the very first example, did anyone here find the laugh after the "winter" answer to be convincing? What was the need for it? Why did the human speaker not get to finish a single sentence or finish a thought before the model took over with a monologue?
I'm absolutely going to hate talking to these things as customer service agents, with fake vocal fry and odd amounts of intonation and emotion peppered in.
For sure there's gonna be people falling in love with them though! I find all the anthropomorphization creepy though.
I've been hearing people talk negatively about vocal fry for ages now with no idea what it meant. But this comment was finally the one that made me go look it up. And today I learned that I speak almost entirely in vocal fry.
I listened after reading your comment, and in the first half of the example, Dessa sounds drunk to me, or at least tipsy. So weirdly, the laugh made sense to me.
OpenAI ruined advanced voice mode for me with that. I’m in the middle of a sentence and it goes “uh huh” and it kills my whole train of thought. It does not make me feel like I’m talking to a real person, it makes me feel like I’m talking to a stupid stupid AI that I hate.
Maybe it's better with lower latency, but I get really annoyed by this with ChatGPT Voice. I almost always start my chat with "I'm gonna ramble, I'll tell you when it's your turn".
Can you instruction-train a duplex model like this? How would that look? I also wonder, if a model trained only on speech can develop world knowledge like this, could you train an image model only on images of text to essentially act as an LLM?
The speech is great, but you can see some cracks even in the first sound bit. near the end he asks the model to speak louder and initially the voice is louder but then goes back to the same level, also losing what she was saying just seconds ago and he has to lead back to the topic.
These full-duplex models are getting very "Her"-ish lately. gpt-live-1 is fantastic. Dessa, though, seems to be aiming at full human parity. There's a huge market for AI girlfriends that they should be looking into in earnest...
human advancement is a function of population, instead of focusing on population decline to solve our resource problems we should focus on efficiency and technology. i am not rooting to revert to the dark ages i really struggle with this ideology of reduction that seems extremely popular. we really take for granted the fragility of human existence we exist in a pico second of reality and could and most likely will be snuffed out eventually, having our own species rooting for this outcome seems suicidal.
No most of us are keen on developing human relationships and intimacy, but it sounds like you view women as a warm fleshlight so I hope that you and your genetic line wind up as dead ends with dry humping a robot as your greatest life accomplishment. Good job lil fella. Give that Claude session your 3.5 inches of American steel.
Both speakers in the examples sound unnatural. The human doesn't know what to talk about and seems to have little confidence. The robot says things that only mostly make sense and draws on, saying ultimately very little. "How's the winter stuff?" e.g. is not a sentence a person would say. I might say "How are you dealing with the snow?" or "Are you looking forward to winter?," but not "How's the winter stuff?" And there's just so many examples like this. Also, I'm not convinced that this "human-like" conversation with filler words and interruptions and pauses is actually what anyone wants, especially in absence of a face to interpret or a real human being to understand behind it. Even if it worked perfectly, it would feel uncanny and artificial because I know the person isn't real.
They sound just as unnatural als the annoying actors in the 'Gilmore Girls' series my daughter keeps on watching and re-watching, i.e. stupid valley girl or whatever it is called witless drivel. In that sense this model is tailor-made to create direct script-to-screen voice-overs for pabulum like that.
> we figured out how to train Dessa on only one NVIDIA GB200 NVL72.
This is the crazy part. It seems pretty smart, and LLMs require 1000x more compute to train. Can this kind of efficiency somehow be achieved with text too?
Not if you want the same model that debugs your C++ to also be able to sort objects by shape and generate a description of a video and pick out a good birthday gift for your cousin
"Oh, uh, yeah, pointers and stacks and stuff, uh – lemme spin up Minimax. Just a sec. Ohhh – ok, see where you're casting that float to a double there, uh, line 72..."
Not bad, but I guess I lack the imagination to envision the use cases for such casual conversation. Other than... I suppose a certain demographic would be lining up to use this as the voice for their AI girlfriend.
Also I seem to be missing where/how they are selling this.
> LLMs need an insane amount of text. Dessa learned language from hundreds of times fewer words (in fairness, LLMs also have to learn C++ and whatever the hell Angular is).
Now that a larger proportion of text is AI, I'm appreciating human-written text more and more; this got a good chuckle out of me.
I have a “style guide” markdown that is pretty expansive
I run an RLHF style loop with me in the middle for all my writing now where I give a voice rant that is over expressive (aka redundant samples of concepts that I want to express clearly) in order to manage lossy compression steps
Then I will manually clean up that last 5% after a half dozen rounds
That sequence goes into the style guide to be referenced as a reasoning chain of thought to map rant > output
It’s been three years of tuning I’d suspect at this point
I've recently been using gemini argon as a voice judge. so it goes claude ( with style guide) -> voice judge with argon -> claude adjusts. I do that in a few loops before it hard stops if it can't reconcile, and pushes to me for review.
I've definitely seen LLMs compose jokes with this structure a lot where "whatever the hell ___ is" is in parenthesis. Not saying this is AI generated tho
I actually thought it sounds really good and natural and it freaked me out in a good way.
You can tell that the robots have no idea of what they're talking about, but the voicing, the emotions, etc, really good.. Like talking to a friend on the phone.
Also creepy, because of the potential for abuse of this technology.
But the interesting part to me is that training on voice only is what allows models to learn emotions - voice transmits a lot of emotional information which text doesn't capture. Language has words for a very limited number of emotions - maybe only the peaks - but there's so many more which we can't describe or transmit via text.
You could determine the phonetic tokens which express different kinds of emotions or 'render' text+emotion using a DSL, etc. Exciting stuff.
Interesting tech, but if these are the hand-picked examples that best represent it, I suppose we're not quite there yet.
The intelligence sounds lacking. At this point, anyway.
But the idea of learning through voice instead of written text might prove fruitful. After all, text isn't strictly native to humans. It's just a tool we've invented.
This feels like a parlor trick where the AI was trained to mimic informal telephone mannerisms. The actual conversations were pretty bad. Lots of style, not much substance basically.
Agreed, it’s incredible and scary how natural and human it sounds. It’s gonna be pretty much impossible for almost anyone to tell if they’re talking to AI
So, I tolerate the "ums" and "ahs" and "uhs" in conversation from humans because they're human. If an AI is going to speak to me (gods forbid), it better be concise and clear and focused, or I'm throwing it out the fucking window.
It is interesting that they've done this reasonably successfully, impressive technology. Novel ideas can have inherent value, absent direct uses they may have, as they can be a stepping stone toward other inventions. But, I'm having a hard time coming up with a use case that isn't predatory or intentionally misleading. Company support agents pretending to be human, for instance. Or, taking the next step on AI girlfriend/boyfriend type interactions. Or, outright scams. Models already do an excellent job with voice cloning, at least for intonation and timbre, adding realistic conversational tics makes it even more likely grandma is going to fall for it when her "nephew" calls needing help.
But, that seems to be extremely common with new tech these days. There's always an angle that is unsavory. Marketing, scams, propaganda, surveillance, killing, that's where the money is, so everything bends toward them.
I also don't get the need for all these imperfections. In some examples it sounds like "she" is half asleep or even tipsy. If I want to talk to an all powered machine that knows my codebase inside out, or that can discuss about technical topics like the universe, science, or a specific technical book, etc... I expect it to be an eloquent speaker, capable of a good cadence, and that's easy to understand. I don't need it to mimic all the imperfections, I want it to be like when I'm talking to a really smart person that keeps me engaged and makes me feel smart.
Especially when you keep in mind that not everyone knows english as their first language. I know he's a bit controversial sometimes but Neil deGrasse Tyson is easy to understand and explained interesting topics in his podcast (I could still understand most of it when I was still getting used to listening to english 15+ years ago).
If conversation is the new interface then we will need UX designers to take care of this.
I came here to say the same thing. I don't want a computer constantly inserting stop words, pauses, laughing unnecessarily and interrupting me. This seems technically impressive but is not something I'd want to interact with.
Call me a skeptic, obviously the voice sounds plausible and very realistic and human-level but where does the intelligence come from if it's only trained on human speech datasets? LLMs are powerful because they can do anything, if you only have a voice corpus I doubt it is as powerful as all written human knowledge. Like when it says "My day was good", what does it actually mean? Or is it just generating plausible slop.
It sounds like it is trained on a lot of podcasts, judging by a quick few second skims over their demo tracks.
Also, the trend of posting on HN with much more sensationalist title first, getting to the front page, then getting the title adjusted by a moderator should probably be penalized; how is 'most authentic ever' not a marketing term? (not just this post, but a bunch of posts recently got to frontpage by making unreasonable claims)
It also seems like it trained on dialog in plays and novels. Some of these responses seem way too "perfect", like a response you would hear in a dramatic soap opera. Honestly it might be using that too. Just my take from listening to first minute or two of dialog.
Really impressive demo. I have to say that, but I do worry with this kind of fidelity to a human interaction that people will get more drawn into AI relationships and replace human contact.
I like voice as a mode of interaction with AI, but it’s always been clear with current tech that I’m talking to AI (and yet folks still got drawn into fantasy relationships thanks to sycophantic models etc) - I imagine with voice models like Dessa that could be worse for humans. This kind of fidelity blurs the lines of who or what the human is talking to and lets humans fall into an isolated world where they believe they are “socializing.”
Now, we could argue this is not a negative, maybe it is actually healthy for those who are looking for social connection or lonely, but my gut feel is that is not the case for most. It worries me that this kind of model will actually cause further deterioration of human socialisation and human-to-human contact.
Yeah. If someone talked to me like that, I’d really want to slap them. I hope no one gets the bright idea of building a customer support bot around this tech.
I know someone who recently came across a scammer where a guy impersonated a sheriff's deputy and tried to get money out of her. She told me the guy sounded like a real sheriff and made her believe the guy until he asked her to pay some money in Bitcoin. I can imagine that this type of scam could go viral soon. Even worse, someone could record our voice and fine-tune a model like this so that it can produce our voice and then talk to our family members to deceive them. It'd be a real trouble.
Totally agree. Those scam calls calling as IRS agent, or outsourced criminal shops that try to steal identity, now this makes it much easier. No more foreign accent. They can hyper optimize to sound like a person from that specific locality.
Already had one call from a scammer AI voice that was pretending to be the official billing dept. of my phone company's larger carrier. Was pretty realistic and beleivable as a human voice, but the very moment i hesitated when asked to provide information.. "you should have that information" i started to say but the agent cut the call at the point between my first and second syllable. The caller ID was already suspect, and when I checked that number it is associated to a sex line. But the voice was polite and official sounding...it wasn't the voice that twigged my suspiciousness. Granny is going to have to start requiring everything via registered mail to not get scammed.
Most recent voice-related tech is using voice as an interface or interaction mode. It’s a means to an and, and the end is the value provided by the reasoning system on the other side of the voice.
This model is clearly not so smart. So the voice is the whole point, there’s not much value beyond it, at least on its own.
What that adds up to is, impersonation. That’s what this is for, impersonating humans.
There's no way I would be able to detect if this was AI from the examples alone. If I got a phone call from a malicious agent using this tech, I probably wouldn't realize it. My plan is to ask a challenge question about a shared memory with people I personally know, if there's something suspicious about a call. I don't know how else to prevent it. It sucks to be this suspicious, but I can't help it.
There's so many potential scenarios.
One scenario: An AI voice trainer trains on someone's social media video posts and get a pretty perfect copy. Then SIM jacks the target's phone number and calls pretending to need help. AIs could be used to mock ransom people, request bail money, ask for a change on a production server, etc.
People with high public visibility are likely targets, especially if they have money and or power. Impersonating them to subordinates would be an easy means of a social engineering attack.
The conversation examples are impressive but this made me say holy shit out loud:
"it runs locally on a MacBook Pro M4 Max or better. And we figured out how to train Dessa on only one NVIDIA GB200 NVL72."
If it really can replicate that low latency + that expressiveness on local devices, that's one heck of an accomplishment for "indie" AI.
Also a speech to speech model it can't do any tool use or you can't guide it much am I mistaken? How will it be used for agentic uses is the part I don't get. Edit: this is response from Argon if anyone was also curious: You are not mistaken about Dessa: because it was trained solely on raw audio with zero text data, it cannot read text system prompts or output code for tool calls on its own. To use it as an agent, developers must either steer it purely through spoken voice instructions or pair it as a conversational "voice front-end" alongside a separate text LLM that listens to the audio and executes the tools in the background.
> > one NVIDIA GB200 NVL72
That’s around ~$4-6 million in hardware cost (one rack, 72 GPUs + accompanying hardware).
that’s a good clarification, skimming some of the comments here I was thinking they trained it on a single GB200 gpu. THAT would be a huge win for indie AI
Edit: Nvidia GB200 does not refer to a single gpu, Nvidia’s naming scheme is very confusing. Considering past gpus were called H100, H200 etc, I thought GB200 would just be a newer GPU, but it does actually refer to their 30+ gpu rack scale systems. The claim of “we trained this on a single rack of gpus” is definitely much less impressive than “we trained this on a single gpu”
> Nvidia GB200 does not refer to a single gpu, Nvidia’s naming scheme is very confusing. Considering past gpus were called H100, H200 etc, I thought GB200 would just be a newer GPU, but it does actually refer to their 30+ gpu rack scale systems.
It's even more confusing than that :)
GB200 = 1 CPU + 2 B200 GPUs (packaged together)
NV72 = A rack of 72 B200 GPUs (or 32 GB200 superchips)
Think of GB200 as something like Apple's 'Ultra' chip. Not exactly, but similar. They fuse the chips together with a very fast interconnect (connection).
> they didn’t have to worry about hosting/billing/subscriptions or any of that yet
Or marketing, which they kinda get for free. So much research goes unseen, there’s huge competition for attention, and most research is very limited in that regard
I would say that’s the biggest factor that makes the team “not indie”
At the same time, like you said, still amazing accomplishment, very cool model, and great work
It is cool but since there is no way to confirm ie. run it, or see it working somewhere, it can be also not real.
I get you are excited to share, but taking into account what your product is, it would be more powerful to let people experience it. As a creator of digital products, why would you put so much text on the homepage, anyhow you get the point.
ya if this is real this is magnitudes better than anything else out there, it honestly feels like it can't be real because its too real, i would be 100% fooled and never even question it wasn't a real person, i was more worried because of that, in that no one would be able to tell and you could have very engaging / emotional conversations that chatgpt/grok/claude etc can't even come close to
reminds me of the last year hype around SesameAILabs/csm, people losing their mind over how realistic it was, only for them to disappear and never ship. sorry can't get hyped over some mp3s.
They're all building the "Her" companion device. It's almost like those transparent touchscreen phones you'd see in SciFi movies that every phone maker would have their research Labs working towards, Nokia morph was one of them.
Those things all look this in concept and in movies, but their practical utility in real life always seems to be lacking. I'd imagine this is the reality what everyone building companion devices are facing.
With the amount of money, RnD and engineers these firms have this seems to be the only reason.
If you actually want your "AI" to interact with anything digital, are these voice-to-voice models going to...use speech to text? How does this model interact with anything that isn't an audio channel?
Passing a Turing test over a 5 minute conversation:
- Text interface: Done
- Voice interface: 5-10 years I’ll predict
The demo is nice, but enough obstacles remain that very few people would mistake it for a human over even a 5 min conversation. Chat systems configured to intentionally impersonate can already get people to mistake them for humans most of the time.
There’s been great progress in this area, direct response modeling, parallel reasoning, but last challenges are huge.
The reality is LLMs still seem dumb much more often without significant reasoning time (test time inference). On that point alone they are still an order of magnitude too slow for convincing interactive latency.
Of course they don’t need to meet this bar to be useful, systems are good enough today for lots of applications. It will just be interesting to see what the final delta ends up being.
Very technically impressive, but the fake conversation with the machine was cringe worthy to me; this pretending to care doesn't make me want to converse at all. The goal for me is to have an intelligent conversation that _adds_ to my experience; whatever I'm working on at the time. The AI girlfriend experience makes me cry inside rather than rejoice.
It sounds good, but...what the hell is it talking about?
The "Huge range in intonation and speed." example. "I had another ollie special". "I ordered a French vanilla latte, special from Maude [or is that Aldi?], springs and waffles, granny smith"...wtf does any of this mean?
She takes a sip of something and her "mouth is on fire...from all the sugar". She repeatedly calls herself "a ding".
The voice seems insanely immersive and uncanny. One issue that the full duplex models always have is tool calling. This is where GPT-Live [1] shines in the sense that you can use it as a fully practical agent. Looking forward to seeing how Dessa folks implement this.
amitport | 12 hours ago
weego | 12 hours ago
superchicken099 | 12 hours ago
kennywinker | 12 hours ago
m348e912 | 9 hours ago
It's up there. I think most humans would be convinced they're talking to a human. I assumed you've used other speech models. They are okay, but not as natural and imperfect as Dessa is.
6879346626 | 6 hours ago
Makes me realize how bad being silent really is.
IshKebab | 12 hours ago
VulgarExigency | 11 hours ago
IshKebab | 12 hours ago
rafram | 9 hours ago
opem | 11 hours ago
paxy | 11 hours ago
switchbak | 11 hours ago
For sure there's gonna be people falling in love with them though! I find all the anthropomorphization creepy though.
bityard | 10 hours ago
bityard | 11 hours ago
csmoak | 7 hours ago
preuceian | 10 hours ago
virtualcharles | 9 hours ago
fy20 | 6 hours ago
JoshTriplett | 2 hours ago
moonu | 11 hours ago
actualwitch | 11 hours ago
ttul | 11 hours ago
M3L0NM4N | 11 hours ago
computerdork | 10 hours ago
awakeasleep | 10 hours ago
computerdork | 9 hours ago
so-gala-massey | 2 hours ago
adastra22 | 6 hours ago
qingcharles | 10 hours ago
taneq | 9 hours ago
m4rtink | 2 hours ago
phoronixrly | 10 hours ago
bvcp | 9 hours ago
phoronixrly | 8 hours ago
pigpop | 6 hours ago
whoanoway | 8 hours ago
Would the logical opposite be eternity for all, and bring back the deceased? LLM plays the Joker, happily imprisoned?
Drupon | 9 hours ago
tarpitt | 5 hours ago
In the future you won't be able to tell.
Drupon | 2 hours ago
nostrebored | 10 hours ago
a34729t | 5 hours ago
63 | 11 hours ago
Mallory_Ringess | 11 hours ago
ricardobeat | 11 hours ago
This is the crazy part. It seems pretty smart, and LLMs require 1000x more compute to train. Can this kind of efficiency somehow be achieved with text too?
freeone3000 | 10 hours ago
mortenjorck | 9 hours ago
bityard | 11 hours ago
Also I seem to be missing where/how they are selling this.
robotresearcher | 9 hours ago
haarts | 11 hours ago
Where is this going?
ByteAtATime | 11 hours ago
Now that a larger proportion of text is AI, I'm appreciating human-written text more and more; this got a good chuckle out of me.
AndrewKemendo | 9 hours ago
I can reliably get my custom models to output a 95% perfect replication of my tone and voice
AspireOne | 9 hours ago
nomel | 8 hours ago
adastra22 | 6 hours ago
AndrewKemendo | 7 hours ago
throwup238 | 6 hours ago
sshine | 8 hours ago
AndrewKemendo | 7 hours ago
I have a “style guide” markdown that is pretty expansive
I run an RLHF style loop with me in the middle for all my writing now where I give a voice rant that is over expressive (aka redundant samples of concepts that I want to express clearly) in order to manage lossy compression steps
Then I will manually clean up that last 5% after a half dozen rounds
That sequence goes into the style guide to be referenced as a reasoning chain of thought to map rant > output
It’s been three years of tuning I’d suspect at this point
sshine | 5 hours ago
I have a somewhat expansive style guide, and it still reeks of Claude.
My cleanup is much closer to 40%, which still makes it worth the effort, but sometimes when speed matters, I'll apologize for the slop.
ipkstef | 3 hours ago
sheepscreek | 7 hours ago
EDIT: Nevermind, see below. I would definitely go with a LoRA though.
AndrewKemendo | 7 hours ago
sigmar | 6 hours ago
I've definitely seen LLMs compose jokes with this structure a lot where "whatever the hell ___ is" is in parenthesis. Not saying this is AI generated tho
delegate | 11 hours ago
But the interesting part to me is that training on voice only is what allows models to learn emotions - voice transmits a lot of emotional information which text doesn't capture. Language has words for a very limited number of emotions - maybe only the peaks - but there's so many more which we can't describe or transmit via text.
You could determine the phonetic tokens which express different kinds of emotions or 'render' text+emotion using a DSL, etc. Exciting stuff.
sgarrity | 11 hours ago
hypfer | 11 hours ago
The intelligence sounds lacking. At this point, anyway.
But the idea of learning through voice instead of written text might prove fruitful. After all, text isn't strictly native to humans. It's just a tool we've invented.
ajam1507 | 11 hours ago
bushido | 10 hours ago
It is kinda scary that we're here already, I can see this being pretty problematic for seniors/public prone to getting scammed.
computerdork | 10 hours ago
lrvick | 10 hours ago
SwellJoe | 10 hours ago
It is interesting that they've done this reasonably successfully, impressive technology. Novel ideas can have inherent value, absent direct uses they may have, as they can be a stepping stone toward other inventions. But, I'm having a hard time coming up with a use case that isn't predatory or intentionally misleading. Company support agents pretending to be human, for instance. Or, taking the next step on AI girlfriend/boyfriend type interactions. Or, outright scams. Models already do an excellent job with voice cloning, at least for intonation and timbre, adding realistic conversational tics makes it even more likely grandma is going to fall for it when her "nephew" calls needing help.
But, that seems to be extremely common with new tech these days. There's always an angle that is unsavory. Marketing, scams, propaganda, surveillance, killing, that's where the money is, so everything bends toward them.
LluisGerard | 10 hours ago
Especially when you keep in mind that not everyone knows english as their first language. I know he's a bit controversial sometimes but Neil deGrasse Tyson is easy to understand and explained interesting topics in his podcast (I could still understand most of it when I was still getting used to listening to english 15+ years ago).
If conversation is the new interface then we will need UX designers to take care of this.
driverdan | 9 hours ago
ilaksh | 10 hours ago
stanfordkid | 10 hours ago
GodelNumbering | 10 hours ago
Also, the trend of posting on HN with much more sensationalist title first, getting to the front page, then getting the title adjusted by a moderator should probably be penalized; how is 'most authentic ever' not a marketing term? (not just this post, but a bunch of posts recently got to frontpage by making unreasonable claims)
chrismarlow9 | 10 hours ago
tourmalinetaco | 5 hours ago
andai | 3 hours ago
YeGoblynQueenne | 9 hours ago
milchek | 10 hours ago
I like voice as a mode of interaction with AI, but it’s always been clear with current tech that I’m talking to AI (and yet folks still got drawn into fantasy relationships thanks to sycophantic models etc) - I imagine with voice models like Dessa that could be worse for humans. This kind of fidelity blurs the lines of who or what the human is talking to and lets humans fall into an isolated world where they believe they are “socializing.”
Now, we could argue this is not a negative, maybe it is actually healthy for those who are looking for social connection or lonely, but my gut feel is that is not the case for most. It worries me that this kind of model will actually cause further deterioration of human socialisation and human-to-human contact.
phainopepla2 | 10 hours ago
The conversation with the AI fake wife was a little creepy, albeit honest about what this tech is probably going to be used for.
superdisk | 10 hours ago
christophilus | 8 hours ago
CyberMacGyver | 5 hours ago
armcat | 10 hours ago
coef2 | 10 hours ago
30minAdayHN | 10 hours ago
notrustincloud | 5 hours ago
exizt88 | 10 hours ago
m_fayer | 10 hours ago
This model is clearly not so smart. So the voice is the whole point, there’s not much value beyond it, at least on its own.
What that adds up to is, impersonation. That’s what this is for, impersonating humans.
iAMkenough | 9 hours ago
so-gala-massey | 2 hours ago
electriclove | 9 hours ago
geniium | 9 hours ago
lkey | 9 hours ago
There's no male or neutral voice.
All examples are of white male software engineers talking to what I assume will be ultimately marketed as a 'girlfriend' bot (or used for love scams).
The single paragraph hand waving at the importance of 'safe AI empathy' doesn't dissuade me at all.
Sell your idea as what it is, yet another 'perfect' woman shaped object a hypothetical man can own and use how he likes.
zamalek | 9 hours ago
elxr | 9 hours ago
Is having a duplex model constantly cutting in with uninteresting quips something people are looking for?
mrinterweb | 9 hours ago
There's so many potential scenarios. One scenario: An AI voice trainer trains on someone's social media video posts and get a pretty perfect copy. Then SIM jacks the target's phone number and calls pretending to need help. AIs could be used to mock ransom people, request bail money, ask for a change on a production server, etc.
People with high public visibility are likely targets, especially if they have money and or power. Impersonating them to subordinates would be an easy means of a social engineering attack.
toddmorey | 9 hours ago
If it really can replicate that low latency + that expressiveness on local devices, that's one heck of an accomplishment for "indie" AI.
skhameneh | 8 hours ago
It's a nice accomplishment, but I think we have very different definitions of "indie".
https://en.wikipedia.org/wiki/Block,_Inc.#
sheepscreek | 7 hours ago
That’s around ~$4-6 million in hardware cost (one rack, 72 GPUs + accompanying hardware).
Many AI shops are funded well into tens of millions if not hundreds, for early rounds.
Also the team size is really small (< 10???). So yes, indie might be a stretch but still very impressive, relatively speaking.
Now taking the other side, they didn’t have to worry about hosting/billing/subscriptions or any of that yet. It’s a research demo at this point.
michelsedgh | 5 hours ago
ctoth | 5 hours ago
tourmalinetaco | 5 hours ago
jedbrooke | 3 hours ago
that’s a good clarification, skimming some of the comments here I was thinking they trained it on a single GB200 gpu. THAT would be a huge win for indie AI
Edit: Nvidia GB200 does not refer to a single gpu, Nvidia’s naming scheme is very confusing. Considering past gpus were called H100, H200 etc, I thought GB200 would just be a newer GPU, but it does actually refer to their 30+ gpu rack scale systems. The claim of “we trained this on a single rack of gpus” is definitely much less impressive than “we trained this on a single gpu”
sheepscreek | 16 minutes ago
It's even more confusing than that :)
Think of GB200 as something like Apple's 'Ultra' chip. Not exactly, but similar. They fuse the chips together with a very fast interconnect (connection).stevage | 3 hours ago
gnabgib | 3 hours ago
[0]: https://www.nvidia.com/en-us/data-center/gb200-nvl72/
[1]: https://www.tomshardware.com/tech-industry/artificial-intell...
nico | an hour ago
Or marketing, which they kinda get for free. So much research goes unseen, there’s huge competition for attention, and most research is very limited in that regard
I would say that’s the biggest factor that makes the team “not indie”
At the same time, like you said, still amazing accomplishment, very cool model, and great work
written-beyond | 8 hours ago
Still extremely impressive but not unheard of.
andai | 3 hours ago
By 2030 we'll have this running on old pentiums.
pdntspa | 2 hours ago
Open weights or GTFO
desireco42 | 8 hours ago
I get you are excited to share, but taking into account what your product is, it would be more powerful to let people experience it. As a creator of digital products, why would you put so much text on the homepage, anyhow you get the point.
sebringj | 8 hours ago
Luke2642 | 8 hours ago
armanj | 8 hours ago
written-beyond | 8 hours ago
Those things all look this in concept and in movies, but their practical utility in real life always seems to be lacking. I'd imagine this is the reality what everyone building companion devices are facing.
With the amount of money, RnD and engineers these firms have this seems to be the only reason.
ambicapter | 8 hours ago
satvikpendem | 8 hours ago
WhitneyLand | 8 hours ago
- Text interface: Done
- Voice interface: 5-10 years I’ll predict
The demo is nice, but enough obstacles remain that very few people would mistake it for a human over even a 5 min conversation. Chat systems configured to intentionally impersonate can already get people to mistake them for humans most of the time.
There’s been great progress in this area, direct response modeling, parallel reasoning, but last challenges are huge.
The reality is LLMs still seem dumb much more often without significant reasoning time (test time inference). On that point alone they are still an order of magnitude too slow for convincing interactive latency.
Of course they don’t need to meet this bar to be useful, systems are good enough today for lots of applications. It will just be interesting to see what the final delta ends up being.
bm-rf | 7 hours ago
chzblck | 5 hours ago
keyle | 7 hours ago
mw888 | 7 hours ago
gnabgib | 7 hours ago
stevage | 3 hours ago
The "Huge range in intonation and speed." example. "I had another ollie special". "I ordered a French vanilla latte, special from Maude [or is that Aldi?], springs and waffles, granny smith"...wtf does any of this mean?
She takes a sip of something and her "mouth is on fire...from all the sugar". She repeatedly calls herself "a ding".
andai | 3 hours ago
Modern problems...
andai | 3 hours ago
https://www.youtube.com/watch?v=D5VN56jQMWM
For real though, it's been bothering me, how did they do this in 2018? (Some kind of symbolic logic based AI?)
Also props to the people at Block, Dessa is very cool :)
MisterMunchkin | 3 hours ago
Conventional LLMs are just running speech to text and then working on the text, so they can’t understand music or humming or any sort of sound.
Barbing | 2 hours ago
>Dessa: Hey, baby.
Block is in the AI girlfriend market? Ew.
hariseldom | an hour ago
armcat | an hour ago
[1] https://openai.com/index/introducing-gpt-live/
rmnwski | 52 minutes ago