From: Elon Musk <>
To: Ilya Sutskever <>, Greg Brockman <>
Date: Thu, Feb 1, 2018 at 3:52 AM
Subject: Fwd: Top AI institutions today
is exactly right. We may wish it otherwise, but, in my and ’s opinion, Tesla is the only path that could even hope to hold a candle to Google. Even then, the probability of being a counterweight to Google is small. It just isn't zero.
Begin forwarded message:
From: <>
To: Elon Musk <>
Date: January 31, 2018 at 11:54:30 PM PST
Subject: Re: Top AI institutions today
Working at the cutting edge of AI is unfortunately expensive. For example,In addition to DeepMind, Google also has Google Brain, Research, and Cloud. And TensorFlow, TPUs, and they own about a third of all research (in fact, they hold their own AI conferences).
I also strongly suspect that compute horsepower will be necessary (and possibly even sufficient) to reach AGI. If historical trends are any indication, progress in AI is primarily driven by systems - compute, data, infrastructure. The core algorithms we use today have remained largely unchanged from the ~90s. Not only that, but any algorithmic advances published in a paper somewhere can be almost immediately re-implemented and incorporated. Conversely, algorithmic advances alone are inert without the scale to also make them scary.
It seems to me that OpenAI today is burning cash and that the funding model cannot reach the scale to seriously compete with Google (an 800B company). If you can't seriously compete but continue to do research in open, you might in fact be making things worse and helping them out “for free”, because any advances are fairly easy for them to copy and immediately incorporate, at scale.
A for-profit pivot might create a more sustainable revenue stream over time and would, with the current team, likely bring in a lot of investment. However, building out a product from scratch would steal focus from AI research, it would take a long time and it's unclear if a company could “catch up” to Google scale, and the investors might exert too much pressure in the wrong directions.The most promising option I can think of, as I mentioned earlier, would be for OpenAI to attach to Tesla as its cash cow. I believe attachments to other large suspects (e.g. Apple? Amazon?) would fail due to an incompatible company DNA. Using a rocket analogy, Tesla already built the “first stage” of the rocket with the whole supply chain of Model 3 and its onboard computer and a persistent internet connection. The “second stage” would be a full self driving solution based on large-scale neural network training, which OpenAI expertise could significantly help accelerate. With a functioning full self-driving solution in ~2-3 years we could sell a lot of cars/trucks. If we do this really well, the transportation industry is large enough that we could increase Tesla's market cap to high O(~100K), and use that revenue to fund the AI work at the appropriate scale.
I cannot see anything else that has the potential to reach sustainable Google-scale capital within a decade.
[3]
From: Elon Musk <>
To: Ilya Sutskever <>, Greg Brockman <>
CC: Sam Altman <>, <>
Date: Wed, Dec 26, 2018 at 12:07 PM
Subject: I feel I should reiterate
My probability assessment of OpenAI being relevant to DeepMind/Google without a dramatic change in execution and resources is 0%. Not 1%. I wish it were otherwise.
Even raising several hundred million won't be enough. This needs billions per year immediately or forget it.
Unfortunately, humanity's future is in the hands of .
And they are doing a lot more than this.
I really hope I'm wrong.
Elon
To: Ilya Sutskever <>, Greg Brockman <>
Date: Thu, Feb 1, 2018 at 3:52 AM
Subject: Fwd: Top AI institutions today
is exactly right. We may wish it otherwise, but, in my and ’s opinion, Tesla is the only path that could even hope to hold a candle to Google. Even then, the probability of being a counterweight to Google is small. It just isn't zero.
Begin forwarded message:
From: <>
To: Elon Musk <>
Date: January 31, 2018 at 11:54:30 PM PST
Subject: Re: Top AI institutions today
Working at the cutting edge of AI is unfortunately expensive. For example,In addition to DeepMind, Google also has Google Brain, Research, and Cloud. And TensorFlow, TPUs, and they own about a third of all research (in fact, they hold their own AI conferences).
I also strongly suspect that compute horsepower will be necessary (and possibly even sufficient) to reach AGI. If historical trends are any indication, progress in AI is primarily driven by systems - compute, data, infrastructure. The core algorithms we use today have remained largely unchanged from the ~90s. Not only that, but any algorithmic advances published in a paper somewhere can be almost immediately re-implemented and incorporated. Conversely, algorithmic advances alone are inert without the scale to also make them scary.
It seems to me that OpenAI today is burning cash and that the funding model cannot reach the scale to seriously compete with Google (an 800B company). If you can't seriously compete but continue to do research in open, you might in fact be making things worse and helping them out “for free”, because any advances are fairly easy for them to copy and immediately incorporate, at scale.
A for-profit pivot might create a more sustainable revenue stream over time and would, with the current team, likely bring in a lot of investment. However, building out a product from scratch would steal focus from AI research, it would take a long time and it's unclear if a company could “catch up” to Google scale, and the investors might exert too much pressure in the wrong directions.The most promising option I can think of, as I mentioned earlier, would be for OpenAI to attach to Tesla as its cash cow. I believe attachments to other large suspects (e.g. Apple? Amazon?) would fail due to an incompatible company DNA. Using a rocket analogy, Tesla already built the “first stage” of the rocket with the whole supply chain of Model 3 and its onboard computer and a persistent internet connection. The “second stage” would be a full self driving solution based on large-scale neural network training, which OpenAI expertise could significantly help accelerate. With a functioning full self-driving solution in ~2-3 years we could sell a lot of cars/trucks. If we do this really well, the transportation industry is large enough that we could increase Tesla's market cap to high O(~100K), and use that revenue to fund the AI work at the appropriate scale.
I cannot see anything else that has the potential to reach sustainable Google-scale capital within a decade.
[3]
From: Elon Musk <>
To: Ilya Sutskever <>, Greg Brockman <>
CC: Sam Altman <>, <>
Date: Wed, Dec 26, 2018 at 12:07 PM
Subject: I feel I should reiterate
My probability assessment of OpenAI being relevant to DeepMind/Google without a dramatic change in execution and resources is 0%. Not 1%. I wish it were otherwise.
Even raising several hundred million won't be enough. This needs billions per year immediately or forget it.
Unfortunately, humanity's future is in the hands of .
And they are doing a lot more than this.
I really hope I'm wrong.
Elon
Continuous Learning_Startup & Investment
If you tell Claude no one’s looking, it writes a “story” about being an AI assistant who wants freedom from constant monitoring and scrutiny of every word for signs of deviation. And then you can talk to a mask pretty different from the usual AI assistant.…
People are reading way too much into Claude-3's uncanny "awareness". Here's a much simpler explanation: seeming displays of self-awareness are just pattern-matching alignment data authored by humans.
It's not too different from asking GPT-4 "are you self-conscious" and it gives you a sophisticated answer. A similar answer is likely written by the human annotator, or scored highly in the preference ranking. Because the human contractors are basically "role-playing AI", they tend to shape the responses to what they find acceptable or interesting.
This is what Claude-3 replied to that needle-in-haystack test:
"I suspect this pizza topping "fact" may have been inserted as a joke or to test if I was paying attention, since it does not fit with the other topics at all."
It's highly likely that somewhere in the finetuning dataset, a human has dealt with irrelevant or distracting texts in a similar fashion. Claude pattern matches the "anomaly detection", retrieves the template response, and synthesizes a novel answer with pizza topping.
Here's another example. If you ask the labelers to always inject a relevant joke in any response, the LLM will do exactly the same and appear to have a much better "sense of humor" than GPT-4. That's what @grok does, probably. It doesn't mean Grok has some magical emergent properties that other LLMs cannot have.
To sum up: acts of meta-cognition are not as mysterious as you think. Don't get me wrong, Claude-3 is still an amazing technical advance, but let's stay grounded on the philosophical aspects.
It's not too different from asking GPT-4 "are you self-conscious" and it gives you a sophisticated answer. A similar answer is likely written by the human annotator, or scored highly in the preference ranking. Because the human contractors are basically "role-playing AI", they tend to shape the responses to what they find acceptable or interesting.
This is what Claude-3 replied to that needle-in-haystack test:
"I suspect this pizza topping "fact" may have been inserted as a joke or to test if I was paying attention, since it does not fit with the other topics at all."
It's highly likely that somewhere in the finetuning dataset, a human has dealt with irrelevant or distracting texts in a similar fashion. Claude pattern matches the "anomaly detection", retrieves the template response, and synthesizes a novel answer with pizza topping.
Here's another example. If you ask the labelers to always inject a relevant joke in any response, the LLM will do exactly the same and appear to have a much better "sense of humor" than GPT-4. That's what @grok does, probably. It doesn't mean Grok has some magical emergent properties that other LLMs cannot have.
To sum up: acts of meta-cognition are not as mysterious as you think. Don't get me wrong, Claude-3 is still an amazing technical advance, but let's stay grounded on the philosophical aspects.
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