Nice read on the rarely-discussed-in-the-open difficulties of training LLMs. Mature companies have dedicated teams maintaining the clusters. At scale, clusters leave the realm of engineering and become a lot more biological, hence e.g. teams dedicated to "hardware health".
It can be a frustrating daily life experience of training large models to "babysit" the training run. You're there carefully monitoring the vital signs of your run: loss spikes, numerical issues, throughput, gradient norms, policy entropy, etc. Every time the run degrades or flatlines (can happen often), you quickly look for the stack trace to see what's up. You have to do this fast or 10,000 GPUs could be idling. Often, it is a new, exotic, scary-looking error you've never seen before so you summon help to see if anyone can see what's up. The worst ones like to occur at 4am. Often no one can, so you just ban some nodes that look a bit sketchy and try to restart the run. Sometimes the run goes down just because you have not earned the favors of your gods that day, so you put a while True: loop around your launch command. The underlying issues can be highly diverse, from some GPUs just getting a bit too hot and suddenly doing incorrect multiplication once in a while, to some router going down and decreasing the networked file system I/O, to someone in the datacenter physically disconnecting a wire as part of an un-communicated maintenance. Sometimes you'll never know.
Another necessary related citation here is the famous OPT-175B logbook and I'd hope more like it can see the light of day in the future. (see chronicles/OPT175B_Logbook.pdf in the git repo)
twitter.com/AIatMeta/statu…
TLDR LLM training runs are significant stress-tests of an overall fault tolerance of a large computing system acting as a biological entity. And when you're shopping around for your compute, think about a lot more than just FLOPs and $. Think about the whole service from hardware to software across storage, networking, and compute. And think about whether the team maintaining it looks like The Avengers and whether you could become best friends.
It can be a frustrating daily life experience of training large models to "babysit" the training run. You're there carefully monitoring the vital signs of your run: loss spikes, numerical issues, throughput, gradient norms, policy entropy, etc. Every time the run degrades or flatlines (can happen often), you quickly look for the stack trace to see what's up. You have to do this fast or 10,000 GPUs could be idling. Often, it is a new, exotic, scary-looking error you've never seen before so you summon help to see if anyone can see what's up. The worst ones like to occur at 4am. Often no one can, so you just ban some nodes that look a bit sketchy and try to restart the run. Sometimes the run goes down just because you have not earned the favors of your gods that day, so you put a while True: loop around your launch command. The underlying issues can be highly diverse, from some GPUs just getting a bit too hot and suddenly doing incorrect multiplication once in a while, to some router going down and decreasing the networked file system I/O, to someone in the datacenter physically disconnecting a wire as part of an un-communicated maintenance. Sometimes you'll never know.
Another necessary related citation here is the famous OPT-175B logbook and I'd hope more like it can see the light of day in the future. (see chronicles/OPT175B_Logbook.pdf in the git repo)
twitter.com/AIatMeta/statu…
TLDR LLM training runs are significant stress-tests of an overall fault tolerance of a large computing system acting as a biological entity. And when you're shopping around for your compute, think about a lot more than just FLOPs and $. Think about the whole service from hardware to software across storage, networking, and compute. And think about whether the team maintaining it looks like The Avengers and whether you could become best friends.
Forwarded from 전종현의 인사이트
어제 생각한 주제와 이에 대한 GPT-4의 답변
---
내가 생각했을 때 AI를 통해서 새로운 형태의 조직과 회사가 많이 탄생할 것 같아. 구체적으로 회사 내부의 체계를 바꿀 수 있는 기술이라고 생각하고 있어.
비유를 들면 월마트는 앞단에서 동네 마트를 가지고 있고, 뒷단에서는 물류창고를 가지고 있었다면, 아마존은 뒷단인 물류창고는 동일한 개념으로 이용하지만, 앞단의 차원에서 인터넷이라는 새로운 기술을 활용해서 동네 마트를 PC로 대체시켰고, 이것이 세계 최고의 회사로 만든 비결이지 않았을까 싶은데,
그렇다면 이번 시대에서 뒷단(예를 들어서 직원)을 AI를 통해 교체/증강 시켜서 엄청나게 큰 회사를 만들 수 있는 기회가 생기지 않을까 싶었어.
이에 대한 너의 전체적인 의견이 궁금하고, 만약 동의한다면 구체적으로 어떤 기회들이 있을지 브레인스토밍 해볼 수 있을까?
---
AI 기술의 발전은 분명히 조직과 회사의 운영 방식에 근본적인 변화를 가져올 수 있는 잠재력을 가지고 있습니다. 아마존이 인터넷을 활용하여 전통적인 소매업의 모델을 혁신한 것처럼, AI도 다양한 산업에서 비슷한 혁신을 일으킬 수 있습니다. AI를 통한 혁신은 주로 업무의 자동화, 의사결정 과정의 최적화, 고객 경험의 향상 등 여러 방면에서 나타날 수 있습니다.
AI가 회사 내부 체계를 바꿀 수 있는 방법:
-업무 자동화: 단순 반복 업무뿐만 아니라, 데이터 분석, 보고서 작성 등 상당수의 지식 노동도 AI를 통해 자동화할 수 있습니다. 이를 통해 인력 자원을 더 창의적이고 가치 있는 업무에 집중시킬 수 있습니다.
-의사결정 지원: AI 기반의 데이터 분석은 비즈니스 의사결정을 더 빠르고 정확하게 만들 수 있습니다. 이는 시장 동향 분석, 소비자 행동 예측, 리스크 관리 등 다양한 분야에서 응용될 수 있습니다.
-고객 서비스 혁신: AI 챗봇, 개인화된 추천 시스템 등은 고객 경험을 개선하고, 서비스 효율성을 높일 수 있습니다. 이는 고객 만족도를 높이고, 더 많은 매출을 창출하는 데 기여할 수 있습니다.
-신제품 및 서비스 개발: AI를 활용하여 새로운 제품이나 서비스를 개발하는 것도 가능합니다. 예를 들어, AI를 이용한 건강 관리 애플리케이션, 개인 맞춤형 교육 솔루션 등이 있습니다.
-원격 근무 및 협업의 최적화: AI 도구를 활용하여 팀 간의 협업을 용이하게 하고, 원격 근무를 보다 효율적으로 만들 수 있습니다. 이는 전세계적인 인재 풀에 접근할 수 있는 가능성을 열어줍니다.
-재무 관리 및 최적화: AI 기반의 재무 관리 시스템은 예산 분석, 자금 흐름 예측, 비용 절감 방안 등을 제시함으로써 기업의 재무 건전성을 향상시킬 수 있습니다.
이러한 기회들은 기업이 자신들의 업무 방식을 재고하고, AI 기술을 통해 어떻게 더 효율적이고 혁신적인 방식으로 전환할 수 있을지 고민하게 만듭니다. 그러나 AI 기술을 채택함에 있어서는 윤리적 고려, 직원 교육 및 적응, 그리고 기술에 대한 지속적인 투자와 개선이 필요합니다. AI를 성공적으로 통합하기 위해서는 이러한 도전 과제를 극복하는 것이 중요합니다.
---
내가 생각했을 때 AI를 통해서 새로운 형태의 조직과 회사가 많이 탄생할 것 같아. 구체적으로 회사 내부의 체계를 바꿀 수 있는 기술이라고 생각하고 있어.
비유를 들면 월마트는 앞단에서 동네 마트를 가지고 있고, 뒷단에서는 물류창고를 가지고 있었다면, 아마존은 뒷단인 물류창고는 동일한 개념으로 이용하지만, 앞단의 차원에서 인터넷이라는 새로운 기술을 활용해서 동네 마트를 PC로 대체시켰고, 이것이 세계 최고의 회사로 만든 비결이지 않았을까 싶은데,
그렇다면 이번 시대에서 뒷단(예를 들어서 직원)을 AI를 통해 교체/증강 시켜서 엄청나게 큰 회사를 만들 수 있는 기회가 생기지 않을까 싶었어.
이에 대한 너의 전체적인 의견이 궁금하고, 만약 동의한다면 구체적으로 어떤 기회들이 있을지 브레인스토밍 해볼 수 있을까?
---
AI 기술의 발전은 분명히 조직과 회사의 운영 방식에 근본적인 변화를 가져올 수 있는 잠재력을 가지고 있습니다. 아마존이 인터넷을 활용하여 전통적인 소매업의 모델을 혁신한 것처럼, AI도 다양한 산업에서 비슷한 혁신을 일으킬 수 있습니다. AI를 통한 혁신은 주로 업무의 자동화, 의사결정 과정의 최적화, 고객 경험의 향상 등 여러 방면에서 나타날 수 있습니다.
AI가 회사 내부 체계를 바꿀 수 있는 방법:
-업무 자동화: 단순 반복 업무뿐만 아니라, 데이터 분석, 보고서 작성 등 상당수의 지식 노동도 AI를 통해 자동화할 수 있습니다. 이를 통해 인력 자원을 더 창의적이고 가치 있는 업무에 집중시킬 수 있습니다.
-의사결정 지원: AI 기반의 데이터 분석은 비즈니스 의사결정을 더 빠르고 정확하게 만들 수 있습니다. 이는 시장 동향 분석, 소비자 행동 예측, 리스크 관리 등 다양한 분야에서 응용될 수 있습니다.
-고객 서비스 혁신: AI 챗봇, 개인화된 추천 시스템 등은 고객 경험을 개선하고, 서비스 효율성을 높일 수 있습니다. 이는 고객 만족도를 높이고, 더 많은 매출을 창출하는 데 기여할 수 있습니다.
-신제품 및 서비스 개발: AI를 활용하여 새로운 제품이나 서비스를 개발하는 것도 가능합니다. 예를 들어, AI를 이용한 건강 관리 애플리케이션, 개인 맞춤형 교육 솔루션 등이 있습니다.
-원격 근무 및 협업의 최적화: AI 도구를 활용하여 팀 간의 협업을 용이하게 하고, 원격 근무를 보다 효율적으로 만들 수 있습니다. 이는 전세계적인 인재 풀에 접근할 수 있는 가능성을 열어줍니다.
-재무 관리 및 최적화: AI 기반의 재무 관리 시스템은 예산 분석, 자금 흐름 예측, 비용 절감 방안 등을 제시함으로써 기업의 재무 건전성을 향상시킬 수 있습니다.
이러한 기회들은 기업이 자신들의 업무 방식을 재고하고, AI 기술을 통해 어떻게 더 효율적이고 혁신적인 방식으로 전환할 수 있을지 고민하게 만듭니다. 그러나 AI 기술을 채택함에 있어서는 윤리적 고려, 직원 교육 및 적응, 그리고 기술에 대한 지속적인 투자와 개선이 필요합니다. AI를 성공적으로 통합하기 위해서는 이러한 도전 과제를 극복하는 것이 중요합니다.
Forwarded from Continuous Learning_Startup & Investment
Search products in 2000s used to be fact-centric or directional (help you navigate to X).
Search is increasingly merging w LLM chat products. Search has now split into 3 types of products:
-Search engine. Help me find facts / get somewhere
-Opinion engine. Here is what my ethics team thinks you should believe (could be via blue links or LLM output)
-Answer engine. Lets get you a synthesis (fact based) on your query
- Advice engine. What should I do next?
e.g query/prompt would be: "Here's my funnel data from the last year. What's the lowest-hanging fruit to improve my conversion?"
"Tell me what I don't know"
What would you rather use?
Search is increasingly merging w LLM chat products. Search has now split into 3 types of products:
-Search engine. Help me find facts / get somewhere
-Opinion engine. Here is what my ethics team thinks you should believe (could be via blue links or LLM output)
-Answer engine. Lets get you a synthesis (fact based) on your query
- Advice engine. What should I do next?
e.g query/prompt would be: "Here's my funnel data from the last year. What's the lowest-hanging fruit to improve my conversion?"
"Tell me what I don't know"
What would you rather use?
Continuous Learning_Startup & Investment
https://youtu.be/lXLBTBBil2U?si=AGrS3M-wQIYhNgei
https://youtu.be/lXLBTBBil2U?t=1091
KPI vs. Early Indicators of Future Success (EIOFS)
Gross margin is a result; it isn't an early indicator. Before a market exists, you still need early indicators of future success. The market does not yet exist, but these are important issues to address. This is how we discovered deep learning and built CUDA at the very beginning.
However, Wall Street didn't believe in this vision. How did you motivate your team?
Nothing changed except the share price. When the share prices dropped by 80%, it was somewhat embarrassing. Just go back to doing your job. Wake up at the same time, prioritize your day in the same way. I go back to what I believe in.
You have to check back with the court of your beliefs. What do you believe in? What are the most important things?
Does my family love me? Checked.
Focus on what matters and go to work. Keep the company focused on the core.
Do you believe something changed? The stock prices changed, but did anything else change? Did the laws of physics change? Did gravity change? Did all the assumptions that we believed in and that led to our decisions change? Because if those changed, you would have to change everything.
But if none of those changed, you change nothing. Keep on going.
KPI vs. Early Indicators of Future Success (EIOFS)
Gross margin is a result; it isn't an early indicator. Before a market exists, you still need early indicators of future success. The market does not yet exist, but these are important issues to address. This is how we discovered deep learning and built CUDA at the very beginning.
However, Wall Street didn't believe in this vision. How did you motivate your team?
Nothing changed except the share price. When the share prices dropped by 80%, it was somewhat embarrassing. Just go back to doing your job. Wake up at the same time, prioritize your day in the same way. I go back to what I believe in.
You have to check back with the court of your beliefs. What do you believe in? What are the most important things?
Does my family love me? Checked.
Focus on what matters and go to work. Keep the company focused on the core.
Do you believe something changed? The stock prices changed, but did anything else change? Did the laws of physics change? Did gravity change? Did all the assumptions that we believed in and that led to our decisions change? Because if those changed, you would have to change everything.
But if none of those changed, you change nothing. Keep on going.
YouTube
Jensen Huang, Founder and CEO of NVIDIA
In this View From The Top interview, Shantam Jain, MBA ’24, speaks with Jensen Huang, Founder and CEO of NVIDIA.
As of March 1, 2024, NVIDIA is the third most valuable company on Wall Street, with over $2T in market value. Jensen shares his experience founding…
As of March 1, 2024, NVIDIA is the third most valuable company on Wall Street, with over $2T in market value. Jensen shares his experience founding…
경쟁보다 연대를
질투보다 배움을
비교보단 감사를
오만보단 호기심을
해야하는 게 아니라 하고싶은 것을
불안을 지나 자신에 대한 확신을
인정보단 자기다움을
자기답고 어려운 길을 선택하길
질투보다 배움을
비교보단 감사를
오만보단 호기심을
해야하는 게 아니라 하고싶은 것을
불안을 지나 자신에 대한 확신을
인정보단 자기다움을
자기답고 어려운 길을 선택하길
Our family has recently seen some tragic, distressing events happening with other families we know. Without too much details, one family witnessed a family loss by suicide, and another family is in deep financial trouble.
One common aspect we could see: someone was in deep trouble but didn’t seek help from others. They were strong-willed (there was absolutely no sign of trouble from outside) and tried to take care of everything by themselves, not even telling everything to their spouses, but couldn’t overcome the breaking point.
We’re all humans. We alone can bear only so much pressure.
Same for founders. Of course you must take ownership and be respectful for other people’s time. But do reach out and ask for help if your leg is jammed under a rock. Don’t try to do everything alone.
Knowing when and how to reach out for help is -- sometimes, quite literally -- one of the life survival
One common aspect we could see: someone was in deep trouble but didn’t seek help from others. They were strong-willed (there was absolutely no sign of trouble from outside) and tried to take care of everything by themselves, not even telling everything to their spouses, but couldn’t overcome the breaking point.
We’re all humans. We alone can bear only so much pressure.
Same for founders. Of course you must take ownership and be respectful for other people’s time. But do reach out and ask for help if your leg is jammed under a rock. Don’t try to do everything alone.
Knowing when and how to reach out for help is -- sometimes, quite literally -- one of the life survival
리더십, 그 강력한 마약
• 리더십과 관리는 혼동되기 쉬운 개념이지만, 본질적으로 다른 것임.
• 관리는 일상적이고 매력적이지 않지만 필요한 업무로, 효율적인 반복 작업으로 조직을 유지함.
• 리더십은 흥미롭고 도전적인 역할로, 단순한 관리를 넘어서 사람들이 최선의 자신이 될 수 있도록 격려하는 능력을 말함.
리더십에 대한 생각
• 좋은 리더는 이론이 아닌 실제 경험을 통해 나타남.
• 리더십은 특정 직책에 국한되지 않고, 상황에 따라 자연스럽게 팀원 간에 흐름을 가져야 함.
• 리더십은 사람들이 자신의 최고를 발휘할 수 있도록 격려하는 능력을 가진 사람에 의해 수행됨.
리더십의 자만
• 리더십을 자칭하는 많은 사람들이 실제로는 역량이 부족하거나, 자신들의 분야에 대한 이해가 부족함.
• 리더십이 없는 기술은 단지 인기나 개인적인 영향력을 추구하는 것에 불과함.
• 리더십을 자칭하는 사람들은 종종 자신들의 역할에 대한 과대평가와 자기중심적인 태도를 보임.
리더십과 자아
• 리더십이라는 칭호는 사람들에게 상태와 도파민을 주입하는 효과가 있으며, 이는 종종 악용됨.
• 리더십의 칭호는 개인의 발전을 저해하고, 자아를 부풀리는 결과를 가져올 수 있음.
• 리더십에 대한 과도한 칭찬은 건강하지 못한 존경을 유발하며, 이는 개인에게 부정적인 영향을 미침.
더 나은 관리와 리더십
• 효과적인 관리자는 팀을 돌보고, 필요한 도구를 제공하며, 업무를 잘 처리함.
• 진정한 리더는 정직하고, 팀원들과의 신뢰를 쌓으며, 조직 내에서 긍정적인 변화를 이끌어냄.
• 리더십은 자연스럽게 발생해야 하며, 강제로 리더십 역할을 맡는 것은 바람직하지 않음.
관련 도서 및 자료
• "High Output Management"은 관리에 대한 실질적인 지침을 제공하는 책임.
• "Managing Humans"는 조직 내 정치와 소문을 관리하는 방법에 대해 설명함.
• Pivotal Software의 운영 모델과 리더십에 대한 통찰력을 제공하는 자료와 팟캐스트가 유익함
https://ludic.mataroa.blog/blog/leadership-is-a-hell-of-a-drug/
• 리더십과 관리는 혼동되기 쉬운 개념이지만, 본질적으로 다른 것임.
• 관리는 일상적이고 매력적이지 않지만 필요한 업무로, 효율적인 반복 작업으로 조직을 유지함.
• 리더십은 흥미롭고 도전적인 역할로, 단순한 관리를 넘어서 사람들이 최선의 자신이 될 수 있도록 격려하는 능력을 말함.
리더십에 대한 생각
• 좋은 리더는 이론이 아닌 실제 경험을 통해 나타남.
• 리더십은 특정 직책에 국한되지 않고, 상황에 따라 자연스럽게 팀원 간에 흐름을 가져야 함.
• 리더십은 사람들이 자신의 최고를 발휘할 수 있도록 격려하는 능력을 가진 사람에 의해 수행됨.
리더십의 자만
• 리더십을 자칭하는 많은 사람들이 실제로는 역량이 부족하거나, 자신들의 분야에 대한 이해가 부족함.
• 리더십이 없는 기술은 단지 인기나 개인적인 영향력을 추구하는 것에 불과함.
• 리더십을 자칭하는 사람들은 종종 자신들의 역할에 대한 과대평가와 자기중심적인 태도를 보임.
리더십과 자아
• 리더십이라는 칭호는 사람들에게 상태와 도파민을 주입하는 효과가 있으며, 이는 종종 악용됨.
• 리더십의 칭호는 개인의 발전을 저해하고, 자아를 부풀리는 결과를 가져올 수 있음.
• 리더십에 대한 과도한 칭찬은 건강하지 못한 존경을 유발하며, 이는 개인에게 부정적인 영향을 미침.
더 나은 관리와 리더십
• 효과적인 관리자는 팀을 돌보고, 필요한 도구를 제공하며, 업무를 잘 처리함.
• 진정한 리더는 정직하고, 팀원들과의 신뢰를 쌓으며, 조직 내에서 긍정적인 변화를 이끌어냄.
• 리더십은 자연스럽게 발생해야 하며, 강제로 리더십 역할을 맡는 것은 바람직하지 않음.
관련 도서 및 자료
• "High Output Management"은 관리에 대한 실질적인 지침을 제공하는 책임.
• "Managing Humans"는 조직 내 정치와 소문을 관리하는 방법에 대해 설명함.
• Pivotal Software의 운영 모델과 리더십에 대한 통찰력을 제공하는 자료와 팟캐스트가 유익함
https://ludic.mataroa.blog/blog/leadership-is-a-hell-of-a-drug/
❤1
• Accenture가 디지털 교육 분야의 선구자인 Udacity를 인수하기로 합의
• Udacity는 온라인 학습의 유연성과 인간 지도의 이점을 결합한 독자적인 기술 과정 개발 및 제공에 깊은 전문성을 가지고 있음
• 인수 금액은 공개되지 않음
• Udacity의 230명 이상의 전문가 팀이 Accenture LearnVantage에 합류할 예정
• Accenture LearnVantage는 Accenture의 고객들에게 기술, 데이터, AI 분야에서 사람들의 재교육 및 업스킬을 돕는 종합적인 기술 학습 및 훈련 서비스를 제공
• 이를 통해 조직을 재창조하고 더 큰 비즈니스 가치를 달성할 수 있도록 지원할 예정
• 이 거래는 규제 검토 및 반독점 감독을 받게 될 예정임
Udacity 관련 정보
• 2011년에 설립된 Udacity는 실무자 수준의 기술 기술 습득을 강조하는 선도적인 학습 접근법으로 인정받았음
• 최근에는 주로 소비자 중심에서 AI 및 기술 분야의 경력 개발을 통한 고객 가치 창출을 목표로 하는 인재 변혁 플랫폼으로 진화함
• 1,400명 이상의 전문가 네트워크와 산업 리더들과 공동으로 창작한 독점 콘텐츠 라이브러리를 통해 195개국에 있는 2천1백만 명 이상의 등록 학습자에게 서비스를 제공함
• 인수 소식과 관련하여 더 많은 사람들에게 기술을 전달할 수 있을 것이라는 입장을 밝힘
• 이전에는 인도의 edtech 회사 Upgrad와 8천만 달러에 대한 논의가 있었으나 결국 Accenture가 인수
• Udacity는 과거에 거의 3억 달러를 모금하고 2015년에 10억 달러의 가치 평가를 받았으나, 만약 8천만 달러가 맞다면 가치가 크게 떨어진 것
Accenture 관련 정보
• Accenture는 세계적인 전문 서비스 회사로, 세계 선도 기업, 정부 및 기타 조직들이 디지털 핵심을 구축하고, 운영을 최적화하며, 수익 성장을 가속화하고, 서비스를 향상시키는 데 도움을 줌
• 약 743,000명의 인재와 혁신을 주도하는 회사로, 120개국 이상의 고객에게 서비스를 제공
• 기술, 클라우드, 데이터, AI 분야에서의 강점과 산업 경험, 기능 전문성, 글로벌 전달 능력을 결합하여 실질적인 결과를 제공
https://newsroom.accenture.com/news/2024/accenture-to-acquire-edtech-leader-udacity-to-accelerate-capabilities-of-accenture-learnvantage
• Udacity는 온라인 학습의 유연성과 인간 지도의 이점을 결합한 독자적인 기술 과정 개발 및 제공에 깊은 전문성을 가지고 있음
• 인수 금액은 공개되지 않음
• Udacity의 230명 이상의 전문가 팀이 Accenture LearnVantage에 합류할 예정
• Accenture LearnVantage는 Accenture의 고객들에게 기술, 데이터, AI 분야에서 사람들의 재교육 및 업스킬을 돕는 종합적인 기술 학습 및 훈련 서비스를 제공
• 이를 통해 조직을 재창조하고 더 큰 비즈니스 가치를 달성할 수 있도록 지원할 예정
• 이 거래는 규제 검토 및 반독점 감독을 받게 될 예정임
Udacity 관련 정보
• 2011년에 설립된 Udacity는 실무자 수준의 기술 기술 습득을 강조하는 선도적인 학습 접근법으로 인정받았음
• 최근에는 주로 소비자 중심에서 AI 및 기술 분야의 경력 개발을 통한 고객 가치 창출을 목표로 하는 인재 변혁 플랫폼으로 진화함
• 1,400명 이상의 전문가 네트워크와 산업 리더들과 공동으로 창작한 독점 콘텐츠 라이브러리를 통해 195개국에 있는 2천1백만 명 이상의 등록 학습자에게 서비스를 제공함
• 인수 소식과 관련하여 더 많은 사람들에게 기술을 전달할 수 있을 것이라는 입장을 밝힘
• 이전에는 인도의 edtech 회사 Upgrad와 8천만 달러에 대한 논의가 있었으나 결국 Accenture가 인수
• Udacity는 과거에 거의 3억 달러를 모금하고 2015년에 10억 달러의 가치 평가를 받았으나, 만약 8천만 달러가 맞다면 가치가 크게 떨어진 것
Accenture 관련 정보
• Accenture는 세계적인 전문 서비스 회사로, 세계 선도 기업, 정부 및 기타 조직들이 디지털 핵심을 구축하고, 운영을 최적화하며, 수익 성장을 가속화하고, 서비스를 향상시키는 데 도움을 줌
• 약 743,000명의 인재와 혁신을 주도하는 회사로, 120개국 이상의 고객에게 서비스를 제공
• 기술, 클라우드, 데이터, AI 분야에서의 강점과 산업 경험, 기능 전문성, 글로벌 전달 능력을 결합하여 실질적인 결과를 제공
https://newsroom.accenture.com/news/2024/accenture-to-acquire-edtech-leader-udacity-to-accelerate-capabilities-of-accenture-learnvantage
Accenture
Accenture to Acquire EdTech Leader Udacity to Accelerate Capabilities of Accenture LearnVantage
Accenture has agreed to acquire Udacity, a digital education pioneer with deep expertise in the development and delivery of proprietary technology courses that blend the flexibility of online learning with the benefits of human instruction.
👍1