正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

AI is the first copyable medium with no model provenance: So when distillation and copying happens, nobody can prove the model belongs to them ↓

Sentient Foundation

114,477 subscribers

11,010 次观看 • 1 个月前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

21 条评论

Sentient 的头像

Sentient1 个月前

This has to change

Sentient Foundation 的头像

Sentient Foundation1 个月前

Stay tuned

KUM∆ 的头像

KUM∆1 个月前

Hopefully, next time Chinese and US AI labs accuse each other of distillation, we’ll finally have something more convincing than “trust me bro.” ↓

Sentient Foundation 的头像

Sentient Foundation1 个月前

Don't just trust, verify.

Franco 的头像

Franco1 个月前

If renaissance artists can prove their work belongs to them, so should builders!

Sentient Foundation 的头像

Sentient Foundation1 个月前

100%

Open AGI 的头像

Open AGI1 个月前

Art and AI models deserve provenance

Sentient Foundation 的头像

Sentient Foundation1 个月前

Artists and builders too

bigoldsandwich 的头像

bigoldsandwich1 个月前

Brilliant

dmitriy 的头像

dmitriy1 个月前

"AI is the first copyable medium with no model provenance" we have a problem right here

Sentient Foundation 的头像

Sentient Foundation1 个月前

Houston, we got a problem

mercy 的头像

mercy1 个月前

I'm glad sentient is fixing a common problem in ai

Sentient Foundation 的头像

Sentient Foundation1 个月前

It's about time

ANAKi 的头像

ANAKi1 个月前

And what are we supposed to do about this? Do we really have nothing?

Sentient Foundation 的头像

Sentient Foundation1 个月前

We'll keep you posted if we figure something out 😉

hieunguyen 的头像

hieunguyen1 个月前

Copying source code leaves detectable traces, but model distillation wipes them out completely. The biggest challenge facing AI today isn't increasing parameter counts it's proving ownership of the model itself!

Joel 的头像

Joel1 个月前

rooting for the sentient team on this. sharing a model shouldn’t mean losing credit for it

Sentient Ecosystem 的头像

Sentient Ecosystem1 个月前

Same problem, different era.

Sentient Foundation 的头像

Sentient Foundation1 个月前

History is repeating itself

Bafspot 的头像

Bafspot1 个月前

Sentient research team is about to fix something important in AI

Mils 的头像

Mils1 个月前

🩷🌸

相关视频

Models cost millions to train and minutes to copy. Fine-tuning and distillation can erase where they came from. Introducing the Fingerprinting Leaderboard, an open benchmark for model provenance — built so the proof lives in the weights, not the paperwork.

Models cost millions to train and minutes to copy. Fine-tuning and distillation can erase where they came from. Introducing the Fingerprinting Leaderboard, an open benchmark for model provenance — built so the proof lives in the weights, not the paperwork.

Sentient Foundation

64,039 次观看 • 29 天前

A throwback to when Iris van Herpen sent a model skydiving to prove her couture belongs to the elements.

Sensitive content

A throwback to when Iris van Herpen sent a model skydiving to prove her couture belongs to the elements.

Pedro Markwardt

102,515 次观看 • 6 个月前

"The most important thing about the intelligence layer is the model.” But what happens when developers can choose from hundreds of them? Vincent Weisser of Prime Intellect joined us for New Defaults to talk open models, model choice, routing, economics, and what happens as intelligence becomes increasingly open and competitive.

"The most important thing about the intelligence layer is the model.” But what happens when developers can choose from hundreds of them? Vincent Weisser of Prime Intellect joined us for New Defaults to talk open models, model choice, routing, economics, and what happens as intelligence becomes increasingly open and competitive.

OpenRouter

17,178 次观看 • 1 个月前

The most useful data comes from real user interactions, feedback, and traces. With self-distillation, your model can learn from production traces even when the original environment can’t be replayed.

The most useful data comes from real user interactions, feedback, and traces. With self-distillation, your model can learn from production traces even when the original environment can’t be replayed.

Applied Compute

13,101 次观看 • 2 个月前

Tesla discontinued the Tesla Model S and Model X to prove to the world they are no longer a car manufacturer.

Tesla discontinued the Tesla Model S and Model X to prove to the world they are no longer a car manufacturer.

Jeremy Judkins

12,803 次观看 • 9 个月前

Here is EVERY AI tool you need to be using in August 2026 I've personally used each for 100+ If you master them and use them all, you'll be a productivity MACHINE The list of the tools are down below. How to use each is in the video! • Best planning model: Fable 5 medium- smartest model out there. Use it to do all your ideation and planning • Best execution model: ChatGPT 5.6 sol medium- best bang for your buck. TONS of usage and incredibly smart • Best AI tool: ChatGPT Voice: the future of interfacing with technology • Best AI agent harness: ChatGPT Desktop app- can do anything any other AI agent can do, but does it better • Best model for building UI/UX/games: Claude Code w/ Claude Opus 5- this model gets a lot of hate. Some of it warranted, most of it not. NOTHING beats Opus 5 for UI • Local model: Qwen 3.6 27b on DGX Spark- best speed and intelligence ratio in local AI • Other must have tools: Buzz from Jack Dorsey. The future of AI is multiplayer, and this is the first true multiplayer AI platform out there

Here is EVERY AI tool you need to be using in August 2026 I've personally used each for 100+ If you master them and use them all, you'll be a productivity MACHINE The list of the tools are down below. How to use each is in the video! • Best planning model: Fable 5 medium- smartest model out there. Use it to do all your ideation and planning • Best execution model: ChatGPT 5.6 sol medium- best bang for your buck. TONS of usage and incredibly smart • Best AI tool: ChatGPT Voice: the future of interfacing with technology • Best AI agent harness: ChatGPT Desktop app- can do anything any other AI agent can do, but does it better • Best model for building UI/UX/games: Claude Code w/ Claude Opus 5- this model gets a lot of hate. Some of it warranted, most of it not. NOTHING beats Opus 5 for UI • Local model: Qwen 3.6 27b on DGX Spark- best speed and intelligence ratio in local AI • Other must have tools: Buzz from Jack Dorsey. The future of AI is multiplayer, and this is the first true multiplayer AI platform out there

Alex Finn

42,136 次观看 • 3 个月前

Satya Nadella says AI has entered its model overhang phase. The capabilities are already here. The frontier is no longer the model. It is what the world can do with it.

Satya Nadella says AI has entered its model overhang phase. The capabilities are already here. The frontier is no longer the model. It is what the world can do with it.

vitrupo

97,878 次观看 • 6 个月前

Asked if China's DeepSeek stole American IP, AI Czar David Sacks says it looks like a technique called distillation was used where a student model can "suck the knowledge" out of the parent model and there is evidence that DeepSeek distilled knowledge from OpenAI's models, which is leading to efforts to develop techniques to prevent future copycats

Asked if China's DeepSeek stole American IP, AI Czar David Sacks says it looks like a technique called distillation was used where a student model can "suck the knowledge" out of the parent model and there is evidence that DeepSeek distilled knowledge from OpenAI's models, which is leading to efforts to develop techniques to prevent future copycats

Tsarathustra

711,002 次观看 • 1 年前

Literally, the first transcription model that you can steer with a prompt. Send audio + a prompt. The model does what you ask. Universal 3 Pro from AssemblyAI is the world's first production model to support this. 2026 is off to a great start!

Literally, the first transcription model that you can steer with a prompt. Send audio + a prompt. The model does what you ask. Universal 3 Pro from AssemblyAI is the world's first production model to support this. 2026 is off to a great start!

Santiago

10,147 次观看 • 9 个月前

💪🏻 This is SO COOL I build an app to count dumbbell reps with an AI model in the browser using Tensorflow.js and a pose detection model

💪🏻 This is SO COOL I build an app to count dumbbell reps with an AI model in the browser using Tensorflow.js and a pose detection model

Wes Bos

4,939,583 次观看 • 1 年前

What happens when you feed an AI images of every building in the United States? The model can take any blurry image and tell you exactly where that image was taken. GeoSpy AI (now Raven) is wild

What happens when you feed an AI images of every building in the United States? The model can take any blurry image and tell you exactly where that image was taken. GeoSpy AI (now Raven) is wild

Daniel Heinen

146,195 次观看 • 5 个月前

Your perfect model is always ready. With Fotor, you can create your own AI model and use it to bring your marketing ideas to life. Generate consistent photos, videos, and campaign assets without the time and cost of traditional photoshoots. One AI model. Endless content. Create your model. Build your brand. Market smarter. Try Fotor AI Today！

Fotor

45,843 次观看 • 4 个月前

Sam Altman says the day is approaching when we can ask an AI model to solve all of physics and it can actually do that

Sam Altman says the day is approaching when we can ask an AI model to solve all of physics and it can actually do that

Tsarathustra

852,780 次观看 • 2 年前

1/ First, how do you benchmark an AI model? You give different models the same test cases, and score them. You can do the same with voice models using Word Error Rate (WER). You generate the audio, transcribe it with a speech recognition (ASR) model, and compare that transcript to the original text. And this tells you whether the model said the right words. But the same sentence can be said correctly, while still being wrong in context.

1/ First, how do you benchmark an AI model? You give different models the same test cases, and score them. You can do the same with voice models using Word Error Rate (WER). You generate the audio, transcribe it with a speech recognition (ASR) model, and compare that transcript to the original text. And this tells you whether the model said the right words. But the same sentence can be said correctly, while still being wrong in context.

Cartesia

10,384 次观看 • 1 个月前

Two videos of Russian interceptor drones with AI-targeting The first is the 'Bolt' UAV, a new model with ~15km range The second is the Yolka, a very common model with 2-3km range. It has no explosives, only kinetic forces

Two videos of Russian interceptor drones with AI-targeting The first is the 'Bolt' UAV, a new model with ~15km range The second is the Yolka, a very common model with 2-3km range. It has no explosives, only kinetic forces

EventsInUkraine

10,509 次观看 • 5 个月前

Big News! Meta just released Segment Anything, a new AI model that can "cut out" any object, in any image/video, with a single click. The model is designed and trained to be promptable, so it can transfer zero-shot to new image distributions and tasks.

Big News! Meta just released Segment Anything, a new AI model that can "cut out" any object, in any image/video, with a single click. The model is designed and trained to be promptable, so it can transfer zero-shot to new image distributions and tasks.

Lior Alexander

290,412 次观看 • 3 年前

Introducing Unbound: The first AI model with no guardrails that runs on your device - Browser, iPhone and Android Zero servers Zero cloud Zero deployment The whole model lives on your phone

Introducing Unbound: The first AI model with no guardrails that runs on your device - Browser, iPhone and Android Zero servers Zero cloud Zero deployment The whole model lives on your phone

EVAL Engine

28,935 次观看 • 5 个月前