Загрузка видео...

Не удалось загрузить видео

На главную

Our infra lets us steer trillion-parameter frontier models in real time: - live, mid-CoT edits to internal activations - directly altering how the model reasons (not just outputs) - stackable edits - no added latency We can make models more Gen Z, more concise, etc.

GoodfireAI's profile picture

Goodfire

23,787 subscribers

29,399 просмотров • 6 месяцев назад •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

Комментарии: 0

Нет доступных комментариев

Здесь появятся комментарии из оригинального поста

Похожие видео

"One of the biggest misconceptions" Cerebras CFO Bob Komin pushes back on the small-models narrative. "We serve all models, and there is no limit to the size of the models that we can serve. Today, we're serving trillion parameter models. We're serving trillion parameter models that are internal for OpenAI today. We are currently running OpenAI 5.4 and 5.5 with them."
0:50

"One of the biggest misconceptions" Cerebras CFO Bob Komin pushes back on the small-models narrative. "We serve all models, and there is no limit to the size of the models that we can serve. Today, we're serving trillion parameter models. We're serving trillion parameter models that are internal for OpenAI today. We are currently running OpenAI 5.4 and 5.5 with them."

Deirdre Bosa

83,925 просмотров • 1 месяц назад

Real-time World Models are the next AI frontier. Today, we reactor are taking the first step towards this reality: our early preview lets you experience worlds generated in real-time, running on our global low-latency infrastructure. Try it now:
0:34

Real-time World Models are the next AI frontier. Today, we reactor are taking the first step towards this reality: our early preview lets you experience worlds generated in real-time, running on our global low-latency infrastructure. Try it now:

Bryce Schmidtchen

8,487,304 просмотров • 1 месяц назад

Real-time World Models are the next AI frontier. Today, we're taking the first step towards this reality: our early preview lets you experience worlds generated in real-time, running on our global low-latency infrastructure. Try it now:
0:33

Real-time World Models are the next AI frontier. Today, we're taking the first step towards this reality: our early preview lets you experience worlds generated in real-time, running on our global low-latency infrastructure. Try it now:

reactor

10,294,686 просмотров • 1 месяц назад

for celebrating Sonic Frontiers 3RD anniversary I tried learning blender just couple weeks and did edits to the frontiers models to make them look more fresh and appealing! "Sonic Characters - Ace Models" MOD IS NOW AVAILABLE!
1:42

for celebrating Sonic Frontiers 3RD anniversary I tried learning blender just couple weeks and did edits to the frontiers models to make them look more fresh and appealing! "Sonic Characters - Ace Models" MOD IS NOW AVAILABLE!

Ace super💥

12,680 просмотров • 7 месяцев назад

Anyone backing Restore Britain, please support me and the edits I make so I can continue to make more. We will have our country back. 🇬🇧
0:32

Anyone backing Restore Britain, please support me and the edits I make so I can continue to make more. We will have our country back. 🇬🇧

News Restore Britain

12,258 просмотров • 1 месяц назад

The most effective AI systems don't rely on a single model. Frontier models provide state-of-the-art performance for complex tasks, while routers automatically select lightweight, open-source models for simpler jobs to optimize accuracy, latency, and cost. Learn more:
0:31

The most effective AI systems don't rely on a single model. Frontier models provide state-of-the-art performance for complex tasks, while routers automatically select lightweight, open-source models for simpler jobs to optimize accuracy, latency, and cost. Learn more:

NVIDIA AI

12,152 просмотров • 3 месяцев назад

We need more ISRO edits for real...
0:29

We need more ISRO edits for real...

Vikranth

20,547 просмотров • 2 месяцев назад

Introducing Model Council in Perplexity. Run three frontier models at once, compare outputs, and get a more accurate, higher‑confidence answer. Available now on web only for Perplexity Max subscribers.
0:41

Introducing Model Council in Perplexity. Run three frontier models at once, compare outputs, and get a more accurate, higher‑confidence answer. Available now on web only for Perplexity Max subscribers.

Perplexity

411,515 просмотров • 4 месяцев назад

Mustafa Suleyman says as more compute is added to AI models they become easier to control, steer and align
0:38

Mustafa Suleyman says as more compute is added to AI models they become easier to control, steer and align

Tsarathustra

25,389 просмотров • 1 год назад

Wait we need to make more Luigi Mangione edits with the song Killah...
0:29

Wait we need to make more Luigi Mangione edits with the song Killah...

M∀YHEM 🇵🇸

73,592 просмотров • 1 год назад

Pocket TTS goes multilingual! Now you can use our 100M-parameter models to generate speech in six languages, fast enough to run real-time without a GPU. We also improved the quality of the English model while keeping the same size. And all of this is open-source.
0:28

Pocket TTS goes multilingual! Now you can use our 100M-parameter models to generate speech in six languages, fast enough to run real-time without a GPU. We also improved the quality of the English model while keeping the same size. And all of this is open-source.

kyutai

29,136 просмотров • 1 месяц назад

🚀 Our "technical" marketer might not be looped in, but today is our biggest launch day yet. We're introducing two new products to serve the inference lifecycle: Model APIs and Training. Model APIs are frontier models running on the Baseten Inference Stack, purpose-built for production. Baseten Training (Beta) provides infra and tooling without limitations for AI models destined for production. Huge shoutout to the many partners and customers we've worked with as we built these two new products—more details below.
0:49

🚀 Our "technical" marketer might not be looped in, but today is our biggest launch day yet. We're introducing two new products to serve the inference lifecycle: Model APIs and Training. Model APIs are frontier models running on the Baseten Inference Stack, purpose-built for production. Baseten Training (Beta) provides infra and tooling without limitations for AI models destined for production. Huge shoutout to the many partners and customers we've worked with as we built these two new products—more details below.

Baseten

35,207 просмотров • 1 год назад

OK, this is insane.. Alibaba just dropped 4 new AI models at Apsara 2025, and they’re wild: → a 1 trillion parameter LLM → a vision model that codes from images → an omni-model for text/audio/video → and a new Wan 2.5 preview for video + audio gen more details below:👇
0:28

OK, this is insane.. Alibaba just dropped 4 new AI models at Apsara 2025, and they’re wild: → a 1 trillion parameter LLM → a vision model that codes from images → an omni-model for text/audio/video → and a new Wan 2.5 preview for video + audio gen more details below:👇

Hamza Khalid

26,707 просмотров • 8 месяцев назад

Introducing ⚡️ Just spent the last week hacking with the new Flux AI image model. It’s 3-5x better than any open-source models that came before. No more hands/text issues. Only thing — it’s hard to get the most from it if you're not a developer. Decided to build an app to make training high quality AI image models easy for everyone :) Finetuning lets you teach the model a custom person, object, style etc. It takes 20 mins -- once it’s done you can generate pretty amazing images like this. You can also combine models to generate multi-subjects, styles, etc Try it out and lmk what you think!
0:30

Introducing ⚡️ Just spent the last week hacking with the new Flux AI image model. It’s 3-5x better than any open-source models that came before. No more hands/text issues. Only thing — it’s hard to get the most from it if you're not a developer. Decided to build an app to make training high quality AI image models easy for everyone :) Finetuning lets you teach the model a custom person, object, style etc. It takes 20 mins -- once it’s done you can generate pretty amazing images like this. You can also combine models to generate multi-subjects, styles, etc Try it out and lmk what you think!

Alex 🇺🇸🇧🇬

658,201 просмотров • 1 год назад

If we train VLAs to respond to diverse multimodal prompts, then we can steer them better: [grasp the carrot]/[move to x,y,z]/[put the carrot on the plate]. With many levels of detail, powerful VLMs can step in and steer the model to success much more often! More below 👇
2:11

If we train VLAs to respond to diverse multimodal prompts, then we can steer them better: [grasp the carrot]/[move to x,y,z]/[put the carrot on the plate]. With many levels of detail, powerful VLMs can step in and steer the model to success much more often! More below 👇

Sergey Levine

20,933 просмотров • 4 месяцев назад

You can now run three frontier models at once and select your orchestrator model directly inside Perplexity Computer. Model Council automatically runs GPT-5.4, Claude Opus 4.6 and Gemini 3.1 Pro simultaneously. Three frontier models. One workflow. Best answer wins.
0:32

You can now run three frontier models at once and select your orchestrator model directly inside Perplexity Computer. Model Council automatically runs GPT-5.4, Claude Opus 4.6 and Gemini 3.1 Pro simultaneously. Three frontier models. One workflow. Best answer wins.

Computer

84,097 просмотров • 3 месяцев назад

Nick says no more based/N-zi Amy Acton edits. "It is hilarious but lets not do that."
0:22

Nick says no more based/N-zi Amy Acton edits. "It is hilarious but lets not do that."

Asuka Groyper 🚬

50,781 просмотров • 1 месяц назад

This is how you can make changes to the edits.
0:44

This is how you can make changes to the edits.

Dipolygabana

3,625,724 просмотров • 1 месяц назад

Gen Z bringing back the ancient lore of AMVs as edits is a healing factor in our society
0:57

Gen Z bringing back the ancient lore of AMVs as edits is a healing factor in our society

iris

51,563 просмотров • 9 месяцев назад

Positron AI wants to run 16 trillion parameter models on a single server.
0:43

Positron AI wants to run 16 trillion parameter models on a single server.

SemiAnalysis

19,957 просмотров • 1 месяц назад