Dessa AI vs GPT Live · Confrontation Acoustique Directe IA contre IA

Dessa AI vs GPT Live (GPT-Live-1) : Confrontation Vocale et Technique

Que se passe-t-il lorsque le modèle pur audio Dessa AI de Block discute en direct avec GPT-Live-1 d'OpenAI ? Écoutez les deux enregistrements officiels non scriptés — en ligne studio et sur haut-parleur bruyant — et observez la gestion des interruptions, de la patience et du backchanneling.

Enregistrement #1 : Ligne Studio — Dessa AI parle avec GPT-Live-1 (2:25)

Extrait non scripté (100.2s–246.0s) où Dessa AI et GPT-Live-1 préparent un braquage de film. Notez les repères à 38.8s (Interruption), 100.8s (Patience) et 128.8s (Backchanneling rapide).

GPT-Live-1 & Dessa AI

Dessa AI Talking to GPT-Live-1 (Studio Feed)

GPT-Live-1 · Dessa AI · 2:26

Duel IA vs IA

Extrait non scripté de 2m25s où Dessa AI discute directement avec GPT-Live-1 d'OpenAI — mettant en évidence l'interruption (38.8s), la patience (100.8s) et le backchanneling rapide (128.8s).

0:00 / 2:26
Aller au moment :
Transcription synchronisée (78)
0:00GPT-Live-1What's on your mind?
0:01Dessa AIum so I have a question about
0:05Dessa AIhow
0:05Dessa AIchat GPT can learn and get smarter
0:08Dessa AIso basically I just want to know
0:10GPT-Live-1That's a good one.
0:11Dessa AIwhat what
0:14Dessa AIwhat are things that could make chat
0:16Dessa AIGPT smarter and what effects could that
0:18Dessa AIhave on the researchers in the field?
0:23GPT-Live-1Let me check a
0:23GPT-Live-1few angles.
0:25GPT-Live-1There are a few big ways chat
0:26GPT-Live-1UPT style systems can get smarter.
0:28Dessa AIfantastic I
0:29GPT-Live-1So
0:29GPT-Live-1better training data, improved training methods
0:33GPT-Live-1like teaching reasoning
0:34GPT-Live-1strategies or better feedback loops, and more
0:38GPT-Live-1compute.
0:39Dessa AImean I've heard about the
0:41Dessa AIYou know, there's Amazon GPUs and
0:45Dessa AIstuff out there now and all that
0:47Dessa AIstuff.
0:47Dessa AII don't know.
0:48Dessa AII guess I'm just like
0:51Dessa AIKind of freaked out about what would
0:53Dessa AIwhat would be the way that chat
0:55Dessa AIGPT can learn
0:57Dessa AIbased off of the
1:00Dessa AIInformation that I'm giving it.
1:03GPT-Live-1me check on that.
1:04GPT-Live-1Ah, right.
1:06GPT-Live-1So two things.
1:07Dessa AIOkay.
1:07GPT-Live-1Chatchity can use what you tell it
1:09GPT-Live-1in a conversation as context.
1:12GPT-Live-1And sometimes there's memory, which can retain
1:14GPT-Live-1facts for future chats.
1:16GPT-Live-1But that's different
1:16GPT-Live-1from training the model.
1:18Dessa AIOh, that's that's what that is
1:19GPT-Live-1Yeah,
1:22GPT-Live-1it doesn't instantly change its billions of
1:24GPT-Live-1parameters
1:25GPT-Live-1from your chat.
1:27GPT-Live-1And there is an important distinction.
1:29GPT-Live-1Your conversation can make it
1:32GPT-Live-1seen more informed without actually making
1:35GPT-Live-1the underlying model smarter.
1:38GPT-Live-1Research is
1:38Dessa AIOkay, that's
1:39GPT-Live-1looking to improve it.
1:41Dessa AIYeah, that's really helpful information.
1:44Dessa AISo I guess
1:46Dessa AIThat's what I'm learning is I don't
1:48Dessa AIneed to be freaking out about information
1:50Dessa AIgoing into
1:50Dessa AIchat GPT because it's not going to
1:53Dessa AIlike make me smarter
1:57Dessa AIin that sense, I guess, right?
2:02GPT-Live-1Exactly.
2:03GPT-Live-1It can make this conversation smarter, but
2:04Dessa AIOkay,
2:07GPT-Live-1it
2:07Dessa AIokay,
2:07GPT-Live-1rewrite the model on the fly.
2:09Dessa AIokay.
2:10GPT-Live-1Think of it in good notes.
2:10Dessa AIThat's good.
2:13GPT-Live-1Yeah, it can remember useful
2:15GPT-Live-1details you share, but the core intelligence
2:18GPT-Live-1doesn't update unless itself is
2:20Dessa AIRight.
2:21GPT-Live-1retrained.
2:22Dessa AIOkay.
2:23GPT-Live-1Safe to share.
2:23Dessa AIThat's really relieving.

Enregistrement #2 : Test de Stress Acoustique — Haut-parleur en Pièce Bruyante (4:17)

Enregistré via un haut-parleur ouvert dans une pièce réverbérante pour tester la gestion de l'écho, des rires simultanés et des collisions de parole.

GPT-Live-1 & Dessa AI

Dessa AI vs GPT-Live-1 (Noisy Room Speakerphone)

GPT-Live-1 · Dessa AI · 4:17

Test de Stress Acoustique

Conversation de 4m17s sur haut-parleur dans une pièce bruyante entre Dessa AI et GPT-Live-1 avec écho et chevauchements.

0:00 / 4:17
Transcription synchronisée (139)
0:00GPT-Live-1Hello, how are you?
0:01Dessa AIHow I
0:03GPT-Live-1Do you know ChatGPT?
0:05Dessa AIdo I
0:06GPT-Live-1Do you know ChatGPT have a voice
0:08GPT-Live-1agent?
0:09Dessa AIguess I
0:10GPT-Live-1Do you know its name is GPT
0:12GPT-Live-1life?
0:14Dessa AIdo
0:15GPT-Live-1Okay, so now I want to talk
0:18GPT-Live-1with it and see
0:21GPT-Live-1If you can like interact with each
0:23GPT-Live-1other well, okay?
0:24Dessa AIOkay, so I just want to go
0:25Dessa AIto the document mode.
0:26Dessa AII'll open up the documents
0:28GPT-Live-1Okay, so hello ChatGPT.
0:29Dessa AIOkay,
0:30GPT-Live-1I have a friend.
0:32GPT-Live-1I want to introduce one friend my
0:33GPT-Live-1friend
0:34Dessa AIoh,
0:34GPT-Live-1So I want you to talk with
0:36Dessa AIokay
0:36GPT-Live-1him.
0:36GPT-Live-1Okay, of course.
0:39GPT-Live-1Hi there
0:40Dessa AIHi, Rick.
0:40GPT-Live-1I'm here and ready to chat.
0:42Dessa AIOh
0:43Dessa AIAwesome.
0:43Dessa AIUm, I'm just I'm curious about your
0:46Dessa AIopinion on
0:47Dessa AIartificial intelligence and what the benefits could
0:51Dessa AIbe.
0:54GPT-Live-1Oh
0:55GPT-Live-1Sorry, I forgot.
0:56GPT-Live-1I'm wearing like can you repeat again?
0:56Dessa AIOh
0:58Dessa AISo, what's an opinion on
0:59GPT-Live-1Sure.
1:00GPT-Live-1Hi, I'm here and ready to chat
1:02Dessa AIartificial
1:03Dessa AIintelligence is
1:07Dessa AIand what the benefits could be for
1:10Dessa AIpeople?
1:11Dessa AII mean, how do you think artificial
1:13Dessa AIintelligence could help me or any of
1:15Dessa AIthe people listen?
1:18GPT-Live-1Great question
1:20Dessa AIOkay.
1:20GPT-Live-1Artificial intelligence is basically computers doing tasks
1:24GPT-Live-1that usually need human intelligence like spotting
1:26Dessa AIOkay.
1:27GPT-Live-1patterns or
1:29GPT-Live-1understanding language,
1:31GPT-Live-1helping make decisions.
1:32Dessa AIOkay.
1:33GPT-Live-1In practical terms, it can help you
1:33Dessa AIOkay,
1:35GPT-Live-1save time
1:36GPT-Live-1by automating boring tasks,
1:39GPT-Live-1help you find useful info faster,
1:42GPT-Live-1or even support learning or creativity.
1:44GPT-Live-1But it works best when you guide
1:46GPT-Live-1it and check its output.
1:48Dessa AIso I know as you said, like
1:51Dessa AIthe benefits could be like speaking up
1:53Dessa AItasks like organizing
1:56Dessa AIdata or even personalization, but how does
1:59Dessa AIartificial intelligence actually learn from
2:02Dessa AIexperience?
2:03Dessa AIIs it learning
2:07Dessa AIbased on past experience purely or is
2:09Dessa AIit learning based on algorithms or
2:12Dessa AIa combination of the two?
2:15GPT-Live-1Yeah, so it's both.
2:17GPT-Live-1The algorithms are the setup
2:20GPT-Live-1and then the experience, that is the
2:22GPT-Live-1data.
2:22Dessa AIOkay.
2:23GPT-Live-1So an AI model doesn't remember like
2:26GPT-Live-1a human.
2:27GPT-Live-1It's trained on large sets of
2:29GPT-Live-1examples and it adjusts internal weights
2:29Dessa AIOkay.
2:32GPT-Live-1so that it can make good
2:33Dessa AIOkay.
2:34GPT-Live-1predictions.
2:34Dessa AISo,
2:35GPT-Live-1Once it's trained, go on.
2:36Dessa AIso, um, is there any risks or
2:40Dessa AIdownsides to artificial intelligence?
2:44GPT-Live-1Yeah,
2:46GPT-Live-1there are some.
2:48GPT-Live-1AI can be biased if
2:49GPT-Live-1the data it's given is biased.
2:51Dessa AIYes.
2:52GPT-Live-1It can also make overconfident mistakes, which
2:55GPT-Live-1is something people need to watch out
2:57GPT-Live-1for.
2:58GPT-Live-1And sometimes it can be used in
3:00GPT-Live-1ways that
3:00GPT-Live-1invade privacy or replace jobs without
3:04GPT-Live-1proper safeguards.
3:06GPT-Live-1So it's really powerful, but needs
3:09GPT-Live-1careful thoughtful use.
3:10Dessa AIOkay.
3:11Dessa AIUm, I, I want it.
3:13Dessa AIBut the reason I wanted to talk
3:16Dessa AIto you and Chantry BT is because
3:18Dessa AII know that you can speak
3:19Dessa AIin multiple different languages.
3:22Dessa AISo I was curious about your opinion
3:25Dessa AIon artificial intelligence.
3:29Dessa AIIs there a way that we could
3:31Dessa AIspread our intelligence
3:33Dessa AIacross the world?
3:35Dessa AIAnd if intelligence,
3:39Dessa AIif AI is like
3:41Dessa AIspreading, do you think that it would
3:44Dessa AIbe a way to like
3:45Dessa AIbring together people or keep people separated?
3:50GPT-Live-1Yeah, so the tack itself doesn't decide.
3:53GPT-Live-1It's really how people
3:54GPT-Live-1choose to use it.
3:56GPT-Live-1If it's built and shared responsibly, it
3:59GPT-Live-1can help translate across
4:00GPT-Live-1languages, it can help share knowledge, it
4:03GPT-Live-1can even connect people, but
4:06Dessa AIOkay, so,
4:07GPT-Live-1if the
4:08GPT-Live-1access isn't equal or if it's concentrated
4:10GPT-Live-1into...
4:12Dessa AIoh, no, that's perfectly part.
4:12GPT-Live-1Sorry, go on.
4:14Dessa AII like what you're saying, because I
4:15Dessa AIwant to talk about what that...

Analyse Chronologique : Pourquoi l'Audio Natif Full-Duplex L'emporte

Interruption⏱ 0:38.8

Cession Instantanée de la Parole en Pleine Phrase

Lorsque les deux modèles commencent à parler simultanément après une pause, Dessa AI détecte la collision en quelques millisecondes et laisse naturellement la parole.

Patience⏱ 1:40.8

Écoute Patiente sans Couper Prematurement

Pendant que GPT-Live-1 développe une longue tirade, Dessa AI suit le contour prosodique plutôt qu'un minuteur de silence fixe.

Backchanneling Rapide⏱ 2:08.8

Acquiescements Sub-Seconde et Rires Partagés

Dessa AI glisse des relances naturelles ('yeah', 'right', rires) tout en écoutant sans voler le tour de parole.

Robustesse Acoustique⏱ Haut-parleur

Résistance à la Réverbération et au Bruit Ambiant

Dans l'enregistrement de 4 minutes sur haut-parleur, Dessa AI adapte sa cadence à l'écho sans halluciner de mots fantômes.

Comparatif d'Architecture : Dessa AI vs GPT-Live-1 / GPT-4o Realtime

Comparaison technique entre l'approche purement acoustique de Block et les modèles vocaux pré-entraînés sur du texte.

DimensionDessa AI (Block)GPT-Live-1 / Modèles Vocaux Pré-entraînés sur Texte
Modalité d'Entraînement100 % audio de conversation humaine de zéro (0 % texte)Pré-entraîné sur des milliers de milliards de tokens texte + post-entraînement audio
Efficacité d'ApprentissageApprend la langue avec 100× moins de mots que les LLM texteExige d'immenses corpus web (milliers de milliards de tokens)
Alternance Full-DuplexModélisation continue des ondes ; chevauchement et cession natifsStreaming hybride ; dépend souvent d'heuristiques de détection de tour
BackchannelingRelances acoustiques sub-seconde sans couper la paroleFait rarement du backchannel en écoutant ; attend ou interrompt
Conscience Acoustique Non VerbaleRéagit directement aux sons ambiants (bip de machine à café)Filtre ou ignore généralement les sons non verbaux
Prosodie Émotionnelle & RiresÉmergente de l'audio conversationnel ; change de ton en cours de phraseContrôlée par prompts de style ou conditionnement synthétique
Calcul d'Entraînement1× baie NVIDIA GB200 NVL72Clusters GPU hyperscale massifs
Inférence Locale sur AppareilPlus rapide que le temps réel sur MacBook Pro (M4 Max+)API Cloud uniquement ; nécessite des GPU de datacenter
Statut de PublicationAperçu de recherche (21 enregistrements ; revue de sécurité)API cloud commerciale et mode vocal grand public

FAQ : Dessa AI vs GPT Live

Qu'est-ce que GPT-Live-1 dans les enregistrements de Dessa AI ?

Dans la publication officielle de Block (block.xyz/dessa), GPT-Live-1 désigne le modèle vocal en direct d'OpenAI mis en conversation directe non scriptée avec Dessa AI.

Pourquoi Dessa AI paraît-il plus naturel lors des interruptions ?

Parce qu'il modélise simultanément les deux flux audio sans passer par du texte ni dépendre d'un détecteur VAD rigide.