Dessa AI vs GPT Live · Confronto Acústico Direto entre IAs

Dessa AI vs GPT Live (GPT-Live-1): Comparação de Áudio e Arquitetura

O que acontece quando colocamos o Dessa AI da Block para conversar ao vivo com o GPT-Live-1 da OpenAI? Ouça as duas gravações oficiais sem roteiro — em linha de estúdio e no viva-voz em sala ruidosa — e veja como o treino exclusivo em fala lida com interrupções, paciência e backchanneling.

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

Gravação #1: Linha de Estúdio — Dessa AI falando com GPT-Live-1 (2:25)

Trecho de uma sessão sem roteiro (100.2s–246.0s) onde Dessa AI e GPT-Live-1 planejam um assalto de cinema. Veja os marcadores em 38.8s (Interrupção), 100.8s (Paciência) e 128.8s (Backchanneling rápido).

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

GPT-Live-1 · Dessa AI · 2:26

Duelo IA vs IA

Gravação sem roteiro de 2m25s do Dessa AI conversando com o GPT-Live-1 da OpenAI — destacando interrupção (38.8s), paciência (100.8s) e backchanneling rápido (128.8s).

0:00 / 2:26

Ir para o momento:

Transcrição 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.

Gravação #2: Teste de Estresse Acústico — Viva-Voz em Sala Ruidosa (4:17)

Gravado em viva-voz aberto em uma sala com eco para testar como Dessa AI e GPT-Live-1 lidam com reverberação, risadas simultâneas e colisões de turno.

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

GPT-Live-1 · Dessa AI · 4:17

Teste de Estresse Acústico

Conversa de 4m17s por viva-voz em sala ruidosa entre Dessa AI e GPT-Live-1 com eco e fala sobreposta.

0:00 / 4:17

Transcrição 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...

Análise de Timestamps: Por Que o Áudio Nativo Full-Duplex Vence

Interrupção⏱ 0:38.8

Cessão Instantânea de Turno no Meio da Frase

Quando ambos os modelos começam a falar juntos após uma pausa, o Dessa AI detecta a colisão acústica em milissegundos e cede a vez com naturalidade.

Paciência⏱ 1:40.8

Silêncio Paciente sem Roubar o Turno

Enquanto o GPT-Live-1 desenvolve uma fala longa, o Dessa AI acompanha o contorno prosódico em vez de cortar por um timer fixo de silêncio.

Backchanneling Rápido⏱ 2:08.8

Confirmações Sub-Segundo e Risadas

O Dessa AI insere confirmações naturais ('yeah', 'right', risos) enquanto ouve sem sequestrar o turno de fala.

Robustez Acústica⏱ Viva-Voz

Resiliência a Eco de Sala e Ruído

Na gravação de 4 minutos no viva-voz, o Dessa AI adapta sua cadência ao eco sem alucinar palavras fantasmas.

Comparativo de Arquitetura: Dessa AI vs. GPT-Live-1 / GPT-4o Realtime

Comparação técnica lado a lado entre a abordagem puramente acústica da Block e modelos multimodais pré-treinados em texto.

Dimensão	Dessa AI (Block)	GPT-Live-1 / Modelos Pré-Treinados em Texto
Modalidade de Treino	100% áudio de conversa humana do zero (0% texto)	Pré-treinado em trilhões de tokens de texto + pós-treino de áudio
Eficiência de Amostras	Aprende o idioma com 100× menos palavras que LLMs de texto	Exige corpus de texto em escala web (trilhões de tokens)
Troca de Turno Full-Duplex	Modelagem contínua de ondas; sobreposição e cessão nativas	Streaming híbrido; frequentemente depende de heurísticas de turno
Backchanneling	Confirmações acústicas sub-segundo sem roubar a vez	Raramente faz backchannel ouvindo; espera ou interrompe tudo
Consciência Acústica Não Verbal	Reage diretamente a sons como o apito de uma cafeteira	Costuma filtrar sons ambientais ou ignorá-los
Prosódia Emocional e Risadas	Emergente do áudio conversacional; muda o tom na frase	Controlada via prompts de estilo ou condicionamento sintético
Computação de Treinamento	1× rack NVIDIA GB200 NVL72	Clusters massivos de GPUs em datacenters
Inferência Local no Dispositivo	Roda mais rápido que o tempo real no MacBook Pro (M4 Max+)	Apenas API na nuvem; exige GPUs de servidor
Status de Lançamento	Prévia de pesquisa (21 gravações; revisão de segurança)	API comercial em nuvem e modo de voz ao consumidor

Perguntas Frequentes: Dessa AI vs GPT Live

O que é o GPT-Live-1 nas gravações do Dessa AI?

Na publicação oficial da Block (block.xyz/dessa), GPT-Live-1 refere-se ao modelo de voz ao vivo da OpenAI colocado em conversa direta sem roteiro com o Dessa AI em dois testes: estúdio e viva-voz.

Por que o Dessa AI soa mais natural nas interrupções?

Porque ele modela continuamente os dois fluxos de áudio sem converter fala em texto nem depender de um detector VAD separado.