Загрузка видео...

Не удалось загрузить видео

На главную

New in M365 Copilot: Council. You can run multiple models on the same prompt at the same time, so you can see where they align and diverge, and understand what each adds.

satyanadella's profile picture

Satya Nadella

8,771,584 subscribers

466,931 просмотров • 5 месяцев назад •via X (Twitter)

ОбразованиеНовости и политикаНаука и технологии
LIVE

Anya Rossi• Live Now

Private livecam show

Комментарии: 0

Нет доступных комментариев

Здесь появятся комментарии из оригинального поста

Похожие видео

Introducing Critique, a new multi-model deep research system in M365 Copilot. You can use multiple models together to generate optimal responses and reports.
0:50

Introducing Critique, a new multi-model deep research system in M365 Copilot. You can use multiple models together to generate optimal responses and reports.

Satya Nadella

1,392,990 просмотров • 5 месяцев назад

I discovered the wildest feature of GitHub Copilot CLI by complete accident last night. You can have models call each other. So you can have Opus, Codex and Gemini all working together in the same chat.🤯
2:17

I discovered the wildest feature of GitHub Copilot CLI by complete accident last night. You can have models call each other. So you can have Opus, Codex and Gemini all working together in the same chat.🤯

Burke Holland

95,018 просмотров • 7 месяцев назад

You have a new Dev Playground for testing existing and upcoming FLUX models: 𝗖𝗼𝗺𝗽𝗮𝗿𝗲 𝗺𝗼𝗱𝗲𝗹𝘀 𝘀𝗶𝗱𝗲-𝗯𝘆-𝘀𝗶𝗱𝗲. Run the same prompt across multiple FLUX models at once and see the differences. 𝗖𝗼𝗻𝘁𝗿𝗼𝗹 𝗽𝗮𝗿𝗮𝗺𝗲𝘁𝗲𝗿𝘀. Adjust API parameters from the UI, so what you test is exactly what you build. 𝗘𝘃𝗮𝗹𝘂𝗮𝘁𝗲. Test quality, latency, and cost. 𝗔𝗹𝘄𝗮𝘆𝘀 𝗰𝘂𝗿𝗿𝗲𝗻𝘁. It launches with our latest models and we'll keep adding new models. Link to try it below.
0:20

You have a new Dev Playground for testing existing and upcoming FLUX models: 𝗖𝗼𝗺𝗽𝗮𝗿𝗲 𝗺𝗼𝗱𝗲𝗹𝘀 𝘀𝗶𝗱𝗲-𝗯𝘆-𝘀𝗶𝗱𝗲. Run the same prompt across multiple FLUX models at once and see the differences. 𝗖𝗼𝗻𝘁𝗿𝗼𝗹 𝗽𝗮𝗿𝗮𝗺𝗲𝘁𝗲𝗿𝘀. Adjust API parameters from the UI, so what you test is exactly what you build. 𝗘𝘃𝗮𝗹𝘂𝗮𝘁𝗲. Test quality, latency, and cost. 𝗔𝗹𝘄𝗮𝘆𝘀 𝗰𝘂𝗿𝗿𝗲𝗻𝘁. It launches with our latest models and we'll keep adding new models. Link to try it below.

Black Forest Labs

15,772 просмотров • 2 месяцев назад

You can visit the same place over and over again and see it differently each time.
1:24

You can visit the same place over and over again and see it differently each time.

ΣZƎ

10,452 просмотров • 2 лет назад

Happy and excited with the new system where you can walk in all four directions and do jumps and platforming at the same time.
0:44

Happy and excited with the new system where you can walk in all four directions and do jumps and platforming at the same time.

Dome

156,844 просмотров • 6 месяцев назад

New Release: Claudex Mode For the first time in mankind claude code and codex will be on the same team On the Blackbox CLI you can send the same task for Claude Code to implement and Codex to verify and test. You can choose more ways where they can collaborate on the same task to get the highest level of performance on your tasks
1:17

New Release: Claudex Mode For the first time in mankind claude code and codex will be on the same team On the Blackbox CLI you can send the same task for Claude Code to implement and Codex to verify and test. You can choose more ways where they can collaborate on the same task to get the highest level of performance on your tasks

BLACKBOX AI

304,664 просмотров • 6 месяцев назад

Ollama 0.2 is here! Concurrency is now enabled by default. This unlocks 2 major features: Parallel requests Ollama can now serve multiple requests at the same time, using only a little bit of additional memory for each request. This enables use cases such as: - Handling multiple chat sessions at the same time - Hosting code completion LLMs for your team - Processing different parts of a document simultaneously - Running multiple agents at the same time Run multiple models Ollama now supports loading different models at the same time. This improves several use cases: - Retrieval Augmented Generation (RAG): both the embedding and text completion models can be loaded into memory simultaneously. - Agents: multiple versions of an agent can now run simultaneously - Running large and small models side-by-side Models are automatically loaded and unloaded based on requests and how much GPU memory is available.
0:23

Ollama 0.2 is here! Concurrency is now enabled by default. This unlocks 2 major features: Parallel requests Ollama can now serve multiple requests at the same time, using only a little bit of additional memory for each request. This enables use cases such as: - Handling multiple chat sessions at the same time - Hosting code completion LLMs for your team - Processing different parts of a document simultaneously - Running multiple agents at the same time Run multiple models Ollama now supports loading different models at the same time. This improves several use cases: - Retrieval Augmented Generation (RAG): both the embedding and text completion models can be loaded into memory simultaneously. - Agents: multiple versions of an agent can now run simultaneously - Running large and small models side-by-side Models are automatically loaded and unloaded based on requests and how much GPU memory is available.

ollama

219,429 просмотров • 2 лет назад

Cursor now natively supports git worktrees. You can run multiple agents in parallel, each with their own isolated copy of the codebase. This is great for comparing models or running the same model multiple times and picking the best result.
0:42

Cursor now natively supports git worktrees. You can run multiple agents in parallel, each with their own isolated copy of the codebase. This is great for comparing models or running the same model multiple times and picking the best result.

Lee Robinson

157,666 просмотров • 10 месяцев назад

Don't waste time choosing between models Introducing Multiple Model Generation: → Test up to 4 models at once → Same prompt. Same settings. Side by side → Find what works best for you, faster Time to pick the diamond of the season
0:21

Don't waste time choosing between models Introducing Multiple Model Generation: → Test up to 4 models at once → Same prompt. Same settings. Side by side → Find what works best for you, faster Time to pick the diamond of the season

Magnific

34,374 просмотров • 7 месяцев назад

Can you really feel so much happiness and so much pain at the same time? 💔
0:43

Can you really feel so much happiness and so much pain at the same time? 💔

Danica

12,256 просмотров • 4 месяцев назад

Can you bike no hands and record the donut at the same time ? ( in Amsterdam)
0:24

Can you bike no hands and record the donut at the same time ? ( in Amsterdam)

Lorenzo TerpsArmy

50,331 просмотров • 1 год назад

Turns out you can tweet and work at the same time.
0:27

Turns out you can tweet and work at the same time.

Fenix Ammunition

68,754 просмотров • 8 месяцев назад

"You can have both. You can compete at the highest levels...and be committed to winning for the sake of the group with total commitment AND you can love each other well, commit to growth first, and live in a place of gratitude and service. You can do both at the same time."
0:25

"You can have both. You can compete at the highest levels...and be committed to winning for the sake of the group with total commitment AND you can love each other well, commit to growth first, and live in a place of gratitude and service. You can do both at the same time."

The Winning Difference

43,545 просмотров • 5 месяцев назад

Iranians and Venezuelans can understand each other because they’ve shared a lot of the same feelings. What do you think? 🇮🇷 🫂 🇻🇪
2:02

Iranians and Venezuelans can understand each other because they’ve shared a lot of the same feelings. What do you think? 🇮🇷 🫂 🇻🇪

Alex_TVzla

19,234 просмотров • 6 месяцев назад

We truly live in a future where you can make fursuits and watch videos in VRChat with friends....at the same time
0:57

We truly live in a future where you can make fursuits and watch videos in VRChat with friends....at the same time

Jack 🍊 🔜 IFC

331,133 просмотров • 2 месяцев назад

“ The giant looks in the mirror and sees nothing… If you can remember to stay on the ground, you can be in the air all at the same time. ” - Donda
1:10

“ The giant looks in the mirror and sees nothing… If you can remember to stay on the ground, you can be in the air all at the same time. ” - Donda

Kanversation™️

29,111 просмотров • 1 год назад

🎨 Introducing fal Sandbox. You can now instantly run the same input across multiple models. Compare hundreds of models from fal’s platform side-by-side for speed, quality, and cost.
0:30

🎨 Introducing fal Sandbox. You can now instantly run the same input across multiple models. Compare hundreds of models from fal’s platform side-by-side for speed, quality, and cost.

fal

816,798 просмотров • 10 месяцев назад

"Two things can be right at the same time. They both can be true... You needed Oxford and Ole Miss more than they needed you, and that can totally be true. And then you can choose a new challenge and go to another place. And so, both of those things are true." - Lane Kiffin
0:53

"Two things can be right at the same time. They both can be true... You needed Oxford and Ole Miss more than they needed you, and that can totally be true. And then you can choose a new challenge and go to another place. And so, both of those things are true." - Lane Kiffin

The Next Round

51,121 просмотров • 3 месяцев назад

Some films understand that loneliness and connection can exist at the same time
4:55

Some films understand that loneliness and connection can exist at the same time

✧˖

109,386 просмотров • 3 месяцев назад

Tired of guessing which AI model is best? 🤔 We've got you covered! 👀 Here's a sneak peek of our new model comparison feature in action! Run the same prompt across multiple models and see which one works best for YOU. Which models are you excited to test? #Inferium #AI #Inference #Compare
0:34

Tired of guessing which AI model is best? 🤔 We've got you covered! 👀 Here's a sneak peek of our new model comparison feature in action! Run the same prompt across multiple models and see which one works best for YOU. Which models are you excited to test? #Inferium #AI #Inference #Compare

Inferium

12,336 просмотров • 1 год назад