NOW BUZZING 헤어컬러가 브라운과 오렌지로 쪼개지는 이… · 코치, 85주년에 '낡음'을 미래로 바꾸… · 프레피룩, 왜 더 플라자에서 다시 태어났…◆
NOW BUZZING 헤어컬러가 브라운과 오렌지로 쪼개지는 이… · 코치, 85주년에 '낡음'을 미래로 바꾸… · 프레피룩, 왜 더 플라자에서 다시 태어났…◆
JELIBI
⌕ SUBSCRIBE
SEOUL · DAILY · ISSUE No.327 WE TRIED IT · THE PICK · BEHIND IT 2026.09.30 · WED
JELIBI
⌕ SUB
Beauty Body Gadget Bites Buzz World
HOME/GADGET/BEHIND IT
GADGET BEHIND IT · 5 MIN READ

메타, 2025년 Llama 10억 다운로드·Meta AI·SAM 3 공개

JD 젤리비 편집국 · 2025.12.19 SHARE · COPY LINK

무슨 발표인가

  • Meta AI 앱 (Llama 4 기반) 및 비디오 피드 Vibes 출시
  • Llama 오픈소스 모델 10억 다운로드 달성
  • SAM 3, SAM 3D, SAM Audio, V-JEPA 등 고급 AI 모델 공개

원문 (영어)

As 2025 comes to a close, we’re looking back at some of our biggest moments of the year. We shared our vision for personal superintelligence, broke ground on cutting-edge AI data centers, strengthened protections for teens, launched products enjoyed by billions of people, and more.

Driving AI Innovation We introduced the Meta AI app , a personalized AI assistant built with Llama 4 that helps you solve problems, create , and navigate your daily life. We also launched Vibes , a new feed of AI videos at the center of the Meta AI app, where you can explore, experiment, and express yourself with AI media tools.

In March, we hit 1 billion downloads of Llama , our open source AI model, and it’s being used by developers and organizations all over the world to drive innovation in areas like national security , space exploration , science , agriculture, healthcare, and education .

On the research side, we shared some of our most innovative AI models yet: SAM 3, SAM 3D , SAM Audio , and V-JEPA . Our new SAM models enable object segmentation using text and visual prompts, 3D reconstruction of objects from a single image, and industry-leading audio segmentation.

V-JEPA improves AI’s ability to navigate the physical world. And our Founder and CEO, Mark Zuckerberg, shared his vision for personal superintelligence , a version of AI that empowers people to live more meaningful, connected lives. Building AI-Optimized Infrastructure Our AI workload is rapidly growing, and we’re building the infrastructure we need to power this growth.

We broke ground on three data centers this year, including an AI-optimized data center in El Paso, Texas that has the ability to scale to 1 gigawatt and another in Beaver Dam Wisconsin , that marked our 30th data center overall.

원문: Meta Newsroom — "AI Breakthroughs, Our Most Advanced Glasses, and More: Meta’s 2025 Highlights" (2025-12-19) 공식 원문: https://about.fb.com/news/2025/12/ai-breakthroughs-advanced-ai-glasses-meta-2025-highlights/

#Meta Newsroom
THE JELIBI BRIEF

A small team that reads too much internet so you don't have to.

SUBSCRIBE →
GADGET

인스로픽, 안전장치 없이 사이버공격 자동화 모델 공개

GADGET

삼성 6개 계열사, AI 인프라 기업 헬릭스에 10억 달러 투자

GADGET

TBC, AWS와 협력해 신경세포 유래 AI 비디오 모델 출시

← GADGET BEHIND IT

메타, 2025년 Llama 10억 다운로드·Meta AI·SAM 3 공개

젤리비 편집국·2025.12.19·5 MIN
IN THIS PIECE
무슨 발표인가 원문 (영어)

무슨 발표인가

  • Meta AI 앱 (Llama 4 기반) 및 비디오 피드 Vibes 출시
  • Llama 오픈소스 모델 10억 다운로드 달성
  • SAM 3, SAM 3D, SAM Audio, V-JEPA 등 고급 AI 모델 공개

원문 (영어)

As 2025 comes to a close, we’re looking back at some of our biggest moments of the year. We shared our vision for personal superintelligence, broke ground on cutting-edge AI data centers, strengthened protections for teens, launched products enjoyed by billions of people, and more.

Driving AI Innovation We introduced the Meta AI app , a personalized AI assistant built with Llama 4 that helps you solve problems, create , and navigate your daily life. We also launched Vibes , a new feed of AI videos at the center of the Meta AI app, where you can explore, experiment, and express yourself with AI media tools.

In March, we hit 1 billion downloads of Llama , our open source AI model, and it’s being used by developers and organizations all over the world to drive innovation in areas like national security , space exploration , science , agriculture, healthcare, and education .

On the research side, we shared some of our most innovative AI models yet: SAM 3, SAM 3D , SAM Audio , and V-JEPA . Our new SAM models enable object segmentation using text and visual prompts, 3D reconstruction of objects from a single image, and industry-leading audio segmentation.

V-JEPA improves AI’s ability to navigate the physical world. And our Founder and CEO, Mark Zuckerberg, shared his vision for personal superintelligence , a version of AI that empowers people to live more meaningful, connected lives. Building AI-Optimized Infrastructure Our AI workload is rapidly growing, and we’re building the infrastructure we need to power this growth.

We broke ground on three data centers this year, including an AI-optimized data center in El Paso, Texas that has the ability to scale to 1 gigawatt and another in Beaver Dam Wisconsin , that marked our 30th data center overall.

원문: Meta Newsroom — "AI Breakthroughs, Our Most Advanced Glasses, and More: Meta’s 2025 Highlights" (2025-12-19) 공식 원문: https://about.fb.com/news/2025/12/ai-breakthroughs-advanced-ai-glasses-meta-2025-highlights/

#Meta Newsroom
THE JELIBI BRIEF

A small team that reads too much internet so you don't have to.

SUBSCRIBE →
MORE IN BEHIND IT
질병관리청, WHO 의료대응수단 네트워크 포럼 참석해 감염병 대응 협력 강화인스로픽, 안전장치 없이 사이버공격 자동화 모델 공개삼성 6개 계열사, AI 인프라 기업 헬릭스에 10억 달러 투자Samsung, 세계 심장의 날 캠페인으로 심장 건강 관리 강조CJ도너스캠프, 아동복지시설 교사 260명 교사교육 실시
THE JELIBI BRIEF

인터넷을 너무 많이 보는 팀이 대신 골라 옵니다.

SUBSCRIBE

바로가기 등록하시면, 더 쉽게 찾아보실 수 있습니다.