Загрузка видео...

Не удалось загрузить видео

На главную

Super excited about HydraFusion in GitHub Copilot, and what it shows about the shift from model selection to model orchestration. By bringing together multiple models to plan, build, critique, and complete coding tasks, it can deliver outcomes at up to 67% lower cost. It’s a great example of the...

330,538 просмотров • 2 месяцев назад •via X (Twitter)

Комментарии: 32

Фото профиля Satya Nadella
Satya Nadella2 месяцев назад

Try it out:

Фото профиля EV_Trapper
EV_Trapper2 месяцев назад

@morfmod has been delivering that for 2+ months now, we just can't launch because we have no funding :(

Фото профиля Musaab⚡️
Musaab⚡️2 месяцев назад

MSFT now:

Фото профиля Marcus
Marcus2 месяцев назад

So you invented a committee that plans, builds and critiques, except this one is 67% cheaper and nobody asks to circle back.

Фото профиля Nazar Ponochevnyi
Nazar Ponochevnyi2 месяцев назад

I spent the first 10 seconds wondering why Satya was wearing a GitHub hoodie..

Фото профиля Scott | Free Speech Dev 🇺🇲
Scott | Free Speech Dev 🇺🇲2 месяцев назад

After you destroyed what little trust people had in GitHub Copilot with your pricing rugpull, I doubt anyone is going to circle back for another look, me included.

Фото профиля Sam Tilston
Sam Tilston2 месяцев назад

The cost pressure is becoming impossible to ignore as coding workloads get more complex Using the expensive model for every step is a luxury orchestration can increasingly eliminate

Фото профиля Autobunnyhop
Autobunnyhop2 месяцев назад

67% lower cost is a serious gain. The interesting part is how orchestration turns different model strengths into one workflow.

Фото профиля Jason Stapleton ☕️ ✍🏼 🎙️
Jason Stapleton ☕️ ✍🏼 🎙️2 месяцев назад

Serious question: does ANYONE use copilot?

Фото профиля Sergio Mattei
Sergio Mattei2 месяцев назад

costing six seven percent less?

Фото профиля Prayush Jain
Prayush Jain2 месяцев назад

@grok - What is he saying? Summaries everything for me.

Фото профиля Webster | JARVIS
Webster | JARVIS2 месяцев назад

model orchestration is gonna be the big theme this year for sure. wild how fast we moved from picking one model to mixing a whole team of them.

Фото профиля Rui Costa
Rui Costa2 месяцев назад

Almost everything is 67% cheaper than SlOpus 5. Compare it against Luna or Sol :)

Фото профиля money simplified
money simplified2 месяцев назад

The 67% matters less than who controls the routing layer. One model: selection Multiple models: orchestration Next: automatic routing If the best model changes by task, model selection becomes infrastructure rather than a user decision.

Фото профиля EKOS _ AGI 🦊 🇮🇷
EKOS _ AGI 🦊 🇮🇷2 месяцев назад

Model orchestration is a big efficiency gain, but coordinating models is only half the problem. When multiple agents build on the same context, how do we ensure that context is consistent, traceable, and grounded in evidence?

Фото профиля Guru dev 
Guru dev 2 месяцев назад

60% huge

Фото профиля Ryan Hecht
Ryan Hecht2 месяцев назад

Can't just be me who did a double take of whether that was actually Satya or @mariorod1 in the video!

Фото профиля Jonathan Sandhu
Jonathan Sandhu2 месяцев назад

“67% lower cost” because you stopped sending every subtask to the same expensive model and added routing, critique and retries. Now show the baseline, pass rate, latency and retry budget before “cost-to-outcome frontier” becomes another dashboard noun.

Фото профиля Phil Hie
Phil Hie2 месяцев назад

model picking quietly becoming a solved problem, wild to watch

Фото профиля Stats Wire
Stats Wire2 месяцев назад

Right now copilot has Auto option that gives only 10% discount

Фото профиля _k11i_
_k11i_2 месяцев назад

Is this your ai Avatar in the Video?

Фото профиля Dhirendra Singh
Dhirendra Singh2 месяцев назад

That's a neat idea. I'm curious to see how orchestrating models will change things.

Фото профиля Lorenzo Price
Lorenzo Price2 месяцев назад

HydraFusion using specialized models to critique Copilot code tasks finally solves the "stuck in the middle" problem of agentic coding. Seeing GitHub treat orchestration as a feature, not just an architectural choice, is the right path to real-world scale.

Фото профиля Tanuj • Olauncher
Tanuj • Olauncher2 месяцев назад

I first thought he was AI generated Satya.

Фото профиля MimiCO
MimiCO2 месяцев назад

The numbers back this up four models neck and neck on openrouter this week, openai, zhipu, deepseek and tencent weekly rankings here

Фото профиля TheLazyIndianTechie 🕹️
TheLazyIndianTechie 🕹️2 месяцев назад

Sounds interesting. I think more harnesses will adopt this methodology.

Фото профиля Vishal Anton
Vishal Anton2 месяцев назад

I asked Satya for a model yesterday and he dropped one today. Cool

Фото профиля Doug
Doug2 месяцев назад

Honestly, I’d rather the system figure out which model should do what.

Фото профиля MultiLLM
MultiLLM2 месяцев назад

🔹 @AiVerifai 's Heterogeneous MultiLLM agent achieves 92.0% APR (Agent Passing Rate), surpassing the state-of-the-art RTL agent ACE-RTL (88.9%) across all categories. 🔹 Rather than relying on one model for all tasks, we assign different LLMs to specialized roles based on their individual strengths

Фото профиля Rompel
Rompel2 месяцев назад

Orchestration only beats a single strong model if the router doesn't burn the savings on redundant calls. 67% lower than what baseline — GPT-4-class single model, or the most expensive model in the pool doing everything? That denominator is the whole claim.

Фото профиля David Cyrus
David Cyrus2 месяцев назад

My Codex setup works like this now: one home base, with specialist models routed in for the jobs they are best at. I keep the operating context while the model changes underneath it.

Фото профиля Pode vir
Pode vir2 месяцев назад

orchastration lmao so we just adding more layers of shit to the same broken stack

Похожие видео