Jack Dorsey 的 Block 做出一个“像尴尬新朋友”一样聊天的 AI 模型Jack Dorsey’s Block made an AI model that talks to you like an awkward new friend


AI free token/AI免费积分
Jack Dorsey 的 Block 做出一个“像尴尬新朋友”一样聊天的 AI 模型

Jack Dorsey 旗下的 Block 发布了一款名为 Dessa 的 AI 模型,它"完全从零开始、只用人类对话训练而成"。为展示模型效果,Block 分享了它与人类聊天的记录——这些对话偶尔会显得有点尴尬和不可思议。

以 Dessa 负责人 Ragavan Thurairatnam 分享的这段对话为例:模型与对话者之间的来回总体自然(不过不知为何,模型一开始把对方错认成了一位叫"Ronaldo"的人)。

还有一段 Dessa 通过语音玩猜谜游戏的视频。Dessa 网站上还有其他示例:一段关于克里斯托弗·诺兰电影的对话(包括 Dessa 意外跑题聊到布莱恩·辛格版超人电影)、一个人告诉 Dessa 要带它去巴黎、给它一个惊喜(据网站描述,Dessa"随后用听起来带着哽咽的感激"回应),以及一段 OpenAI 的 GPT-Live-1 语音模型与 Dessa 之间的对话(Dessa 显得更自然)。上述部分对话音频可在视频中收听。

文章配图

在官方网站上,Dessa 团队表示 Dessa 是"真正的语音到语音(speech-to-speech)模型,它所知道的一切都来自人类语音",并且可以在 MacBook Pro M4 Max"或更高配置"上本地运行。至于为什么要做它,团队给出三个理由:"好奇(也就是好玩)、更好地促进人类与 AI 之间的理解,以及安全",并做了进一步说明:

婴儿学说话时从没见过一个书面单词,我们想看看一个模型能不能也这样。它可以。只是非常难。

文章配图

语音是通向任何智能(无论超级与否)最自然的界面,而今天的语音 AI 在浪费它。它把我们说的话压平成文本,跟不上人类的说话节奏。

AI 不断获得力量与独立性,却几乎听不到我们声音里的情绪。想象一下你正处在剧痛中,而一个语音 AI 毫无察觉、还在自说自话。这就是安全问题。Dessa 是朝着解决它迈出的一步。

文章配图

Dessa 团队表示,将向"一小群 AI 安全研究人员"开放模型的早期访问。

本文来源:https://www.theverge.com/ai-artificial-intelligence/1017906/jack-dorsey-block-de
若有版权问题,请来信告知:13951431913#139.com 或在右方提交评论。

Jack Dorsey’s Block announced an AI model called Dessa that’s trained “from scratch on nothing but human conversation,” and to show off the model, Block shared chats it has had with humans that can occasionally be a little awkward and uncanny.

Take this one, for example, shared by Dessa lead Ragavan Thurairatnam. The conversation between the model and the speaker does have a mostly natural back and forth (though for some reason, the model initially mistakes the speaker for somebody named “Ronaldo”).

[Media: https://twitter.com/RagavanThurair/status/2113671324400861645]

文章配图

[Media: https://twitter.com/RagavanThurair/status/2113704911749911028]

The Dessa website features a few other examples, like a back-and-forth about Christopher Nolan’s films (including Dessa going on an unexpected tangent about Bryan Singer’s Superman films), a person telling Dessa about taking it on a surprise trip to Paris (to which Dessa, as the website describes, “then answers with what sounds like teary gratitude”), and a conversation between OpenAI’s GPT-Live-1 voice model and Dessa (where Dessa comes across as more natural). You can hear clips from some of those conversations in this video.

[Media: https://twitter.com/RagavanThurair/status/2113691903866872251]

文章配图

On the website, the Dessa team says that Dessa is a “true speech-to-speech model, and everything it knows came from human speech,” and it can run locally on a MacBook Pro M4 Max “or better.” As for why they made it, the team gives the three reasons “curiosity (aka fun), better understanding between humans and AI, and safety,” and provided some more detail:

> Babies learn to talk without ever seeing a word written down. We wanted to see if a model could too. It can. It’s just very hard.

> Speech is the most natural interface to any intelligence, super or otherwise, and today’s voice AI wastes it. It flattens what we say into text and can’t keep up with human timing.

文章配图

> AI keeps gaining power and independence, and it’s still nearly deaf to the emotion in our voices. Imagine being in serious pain while a voice AI has no idea and just keeps going. That’s the safety problem. Dessa is a step toward fixing it.

The Dessa team says it will be giving “a small group of AI safety researchers” early access to the model.

Jack Dorsey’s Block made an AI model that talks to you like an awkward new friend

暂无评论,快来发表第一条评论吧!No comments yet. Be the first!

📮 需求咨询📮 Inquiry