Dessa AI vs GPT Live · Duelo Acústico Directo entre Modelos de IA

Dessa AI vs GPT Live (GPT-Live-1): Duelo de Voz y Arquitectura

¿Qué ocurre cuando pones al modelo puramente acústico Dessa AI de Block a conversar en vivo con GPT-Live-1 de OpenAI? Escucha las dos grabaciones oficiales sin guion —en línea de estudio y por altavoz con ruido— y analiza cómo responde ante interrupciones, pausas y retroalimentación rápida.

Studio Line Recording (2:25)Noisy Speakerphone Stress Test (4:17)Architecture Matrix

Grabación #1: Línea de Estudio — Dessa AI conversando con GPT-Live-1 (2:25)

Extracto de una sesión sin guion (100.2s–246.0s) donde Dessa AI y GPT-Live-1 planean un atraco de película. Observa los marcadores en 38.8s (Interrupción), 100.8s (Paciencia) y 128.8s (Backchanneling rápido).

Dessa AI Conversando con GPT-Live-1 (Estudio)

GPT-Live-1 · Dessa AI · 2:26

Duelo IA vs IA

Extracto sin guion de 2m25s entre Dessa AI y GPT-Live-1 de OpenAI, destacando cesión por interrupción (38.8s), paciencia (100.8s) y backchanneling rápido (128.8s).

0:00 / 2:26

Saltar al momento:

Transcripción sincronizada (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.

Grabación #2: Prueba de Estrés Acústico — Altavoz en Sala Ruidosa (4:17)

Grabado mediante altavoz abierto en una habitación con reverberación para evaluar cómo ambos modelos gestionan el eco, las risas simultáneas y los choques de turno.

Dessa AI vs GPT-Live-1 (Altavoz con Ruido)

GPT-Live-1 · Dessa AI · 4:17

Estrés Acústico

Conversación de 4m17s por altavoz en una sala con eco y ruido entre Dessa AI y GPT-Live-1.

0:00 / 4:17

Transcripción sincronizada (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...

Análisis por Marcas de Tiempo: Por Qué Gana el Audio Nativo Full-Duplex

Interrupción⏱ 0:38.8

Cesión Instantánea del Turno a Mitad de Frase

Cuando ambos modelos empiezan a hablar a la vez tras una pausa, Dessa AI detecta la colisión acústica en milisegundos y cede la palabra con naturalidad.

Paciencia⏱ 1:40.8

Escucha Paciente sin Robar el Turno Prematuramente

Mientras GPT-Live-1 desarrolla una idea larga, Dessa AI sigue la entonación prosódica de la frase en lugar de cortar por un temporizador fijo de silencio.

Backchanneling Rápido⏱ 2:08.8

Asentimientos Sub-Segundo y Risa Compartida

Dessa AI introduce breves apoyos vocales ('yeah', 'right', risas) mientras escucha sin interrumpir el discurso del interlocutor.

Robustez Acústica⏱ Altavoz

Resistencia a Reverberación y Ruido de Sala

En la prueba de 4 minutos por altavoz, Dessa AI adapta su cadencia al eco de la habitación sin alucinar palabras fantasma.

Comparativa de Arquitectura: Dessa AI vs. GPT-Live-1 / GPT-4o Realtime

Comparación técnica entre el enfoque puramente acústico de Block y los modelos de voz basados en preentrenamiento de texto.

Dimensión	Dessa AI (Block)	GPT-Live-1 / Modelos Preentrenados con Texto
Modalidad de Entrenamiento	100% audio de conversación humana desde cero (0% texto)	Preentrenado con billones de tokens de texto + post-entrenamiento de audio
Eficiencia de Muestras	Aprende el idioma con 100× menos palabras que los LLM de texto	Requiere corpus de texto a escala web (billones de tokens)
Toma de Turnos Full-Duplex	Modelado continuo de ondas; superposición y cesión nativas	Streaming híbrido; suele depender de heurísticas de detección de turno
Backchanneling	Asentimientos acústicos sub-segundo sin robar el turno	Rara vez asiente mientras escucha; espera o interrumpe por completo
Conciencia Acústica Ambiental	Reacciona directamente a sonidos como el timbre de una cafetera	Suele filtrar sonidos no verbales o ignorarlos
Prosodia Emocional y Risa	Emergente del audio conversacional; cambia de tono a mitad de frase	Controlada mediante prompts de estilo o condicionamiento sintético
Cómputo de Entrenamiento	1× rack NVIDIA GB200 NVL72	Clústeres masivos de centros de datos
Inferencia Local en Dispositivo	Más rápido que el tiempo real en MacBook Pro (M4 Max+)	Solo API en la nube; requiere GPU de centro de datos
Estado de Lanzamiento	Vista previa de investigación (21 grabaciones; revisión de seguridad)	API comercial en la nube y modo de voz de consumo

Preguntas Frecuentes: Dessa AI vs GPT Live

¿Qué es GPT-Live-1 en las grabaciones de Dessa AI?

En la publicación oficial de Block (block.xyz/dessa), GPT-Live-1 es el modelo de voz en vivo de OpenAI puesto a conversar directamente sin guion con Dessa AI.

¿Por qué Dessa AI suena más natural durante las interrupciones?

Porque modela simultáneamente ambos canales de audio sin convertir la voz en texto ni depender de un detector VAD rígido.