Forwarded from BZCF | 비즈까페
BZCF 텔레그램 : https://news.1rj.ru/str/bzcftel
유니클로 야나이 다다시 회장의 2005년 직원들에게 작성한 이메일의 일부입니다. 제가 메모처럼 적어두고, 주기적으로 읽어 보는 글입니다.
2005년은 다다시 회장이 다시 유니클로로 돌아왔던 시기였습니다. 당시 유니클로는 적당히 큰 대기업이 되었고, 사람들은 '적당히 하자' 주의가 팽배했었습니다. 규모도 ‘적당히’ 컸다는 것이, 현재의 유니클로와 같이 글로벌한 회사는 아니었고 정말로 '적당히'였습니다.
그런 시기에, 제2의 창업을 선언하고, 기존의 것들을 완전 새로 하자는 말을 했었고요. 그 후 20년이 지나서... 패션 업계에서 유일무이한 아시아 최초로 글로벌한 회사가 되었네요. 없던 것을 창업하는 것도 어렵지만... 이미 세팅된 문화를 갈아 끼우는 것이 더 힘들었을 것이라 생각이 듭니다. 그의 책을 다시 펼쳐 읽다가, 이 구절이 인상 깊게 다가와 필사하였습니다.
https://m.blog.naver.com/bizucafe/223128943351
유니클로 야나이 다다시 회장의 2005년 직원들에게 작성한 이메일의 일부입니다. 제가 메모처럼 적어두고, 주기적으로 읽어 보는 글입니다.
2005년은 다다시 회장이 다시 유니클로로 돌아왔던 시기였습니다. 당시 유니클로는 적당히 큰 대기업이 되었고, 사람들은 '적당히 하자' 주의가 팽배했었습니다. 규모도 ‘적당히’ 컸다는 것이, 현재의 유니클로와 같이 글로벌한 회사는 아니었고 정말로 '적당히'였습니다.
그런 시기에, 제2의 창업을 선언하고, 기존의 것들을 완전 새로 하자는 말을 했었고요. 그 후 20년이 지나서... 패션 업계에서 유일무이한 아시아 최초로 글로벌한 회사가 되었네요. 없던 것을 창업하는 것도 어렵지만... 이미 세팅된 문화를 갈아 끼우는 것이 더 힘들었을 것이라 생각이 듭니다. 그의 책을 다시 펼쳐 읽다가, 이 구절이 인상 깊게 다가와 필사하였습니다.
https://m.blog.naver.com/bizucafe/223128943351
NAVER
회사도 개인도 성장하지 않으면 죽은 것
2005년 연초에 '제2의 창업'의 방침을 여러분에게 제시한 바 있습니다. 작년 한 해는 연초에 말...
theinformation.com/articles/why-youtube-could-give-google-an-edge-in-ai
Summarize this contents and derive key insights as a ai related startup founder and investor via Perplexity copilot feature.
#1 As an AI startup founder and investor, here are some key insights from the provided search results:
Google's ownership of YouTube could give it an edge in AI. YouTube is the single biggest and richest source of imagery, audio, and text trannoscripts on the internet, and Google's researchers have been using it to develop its next large-language model, Gemini. OpenAI has also secretly used data from YouTube to train some of its AI models.
#2 Open-source AI is gaining on Google and ChatGPT. Meta Platforms gave academics access to sophisticated machine-learning models that can understand conversational language, which they turned into open-source software that powered free alternatives to ChatGPT and other proprietary AI software. Free AI models are now "reasonably close" in performance to proprietary models from Google and ChatGPT creator OpenAI, and most software developers will eventually opt to use the free ones
#3 Google and DeepMind are working together to develop software to compete with OpenAI. Known internally as Gemini, the joint effort began in recent weeks, after Google stumbled with Bard, its first attempt to compete with OpenAI's chatbot
#4 Generative AI startups need their own data. Google, Amazon, Meta Platforms, and Microsoft are jostling to develop products that use generative AI. Startups such as Denoscript, which uses generative artificial intelligence to shortcut the laborious video-editing process, are trying to immunize themselves from looming big tech competition
#5 The European antitrust case against Google might or might not matter. The Europeans have concluded, in a preliminary way, that Google favors its own "online display advertising technology services to the detriment of competing providers". This is no small matter, as Google controls the tools most commonly used by both websites selling ad space and marketers buying ad space on websites across the internet. However, it remains to be seen whether this case will have a significant impact on Google's AI-related activities.
#6 Google is preparing to teach foreign languages through Google Search. The project, referred to internally as Tivoli, grew out of its Google Research unit and is likely to be rolled out later this year.
#7 The creator economy is facing challenges and opportunities with AI. Dmitry Shapiro and Sean Thielen, the co-founders of a startup that developed Koji, a tool that offers link-in-bio landing pages to house creators' digital storefronts, are planning to focus on a new AI product they're developing called YouAI. However, venture capitalists such as Ben Mathews are predicting a wave of failures among creator economy startups as they run out of cash
Summarize this contents and derive key insights as a ai related startup founder and investor via Perplexity copilot feature.
#1 As an AI startup founder and investor, here are some key insights from the provided search results:
Google's ownership of YouTube could give it an edge in AI. YouTube is the single biggest and richest source of imagery, audio, and text trannoscripts on the internet, and Google's researchers have been using it to develop its next large-language model, Gemini. OpenAI has also secretly used data from YouTube to train some of its AI models.
#2 Open-source AI is gaining on Google and ChatGPT. Meta Platforms gave academics access to sophisticated machine-learning models that can understand conversational language, which they turned into open-source software that powered free alternatives to ChatGPT and other proprietary AI software. Free AI models are now "reasonably close" in performance to proprietary models from Google and ChatGPT creator OpenAI, and most software developers will eventually opt to use the free ones
#3 Google and DeepMind are working together to develop software to compete with OpenAI. Known internally as Gemini, the joint effort began in recent weeks, after Google stumbled with Bard, its first attempt to compete with OpenAI's chatbot
#4 Generative AI startups need their own data. Google, Amazon, Meta Platforms, and Microsoft are jostling to develop products that use generative AI. Startups such as Denoscript, which uses generative artificial intelligence to shortcut the laborious video-editing process, are trying to immunize themselves from looming big tech competition
#5 The European antitrust case against Google might or might not matter. The Europeans have concluded, in a preliminary way, that Google favors its own "online display advertising technology services to the detriment of competing providers". This is no small matter, as Google controls the tools most commonly used by both websites selling ad space and marketers buying ad space on websites across the internet. However, it remains to be seen whether this case will have a significant impact on Google's AI-related activities.
#6 Google is preparing to teach foreign languages through Google Search. The project, referred to internally as Tivoli, grew out of its Google Research unit and is likely to be rolled out later this year.
#7 The creator economy is facing challenges and opportunities with AI. Dmitry Shapiro and Sean Thielen, the co-founders of a startup that developed Koji, a tool that offers link-in-bio landing pages to house creators' digital storefronts, are planning to focus on a new AI product they're developing called YouAI. However, venture capitalists such as Ben Mathews are predicting a wave of failures among creator economy startups as they run out of cash
The Information
Why YouTube Could Give Google an Edge in AI
Google last month upgraded its Bard chatbot with a new machine-learning model that can better understand conversational language and compete with OpenAI’s ChatGPT. As Google develops a sequel to that model, it may hold a trump card: YouTube. The video site…
Continuous Learning_Startup & Investment
https://youtu.be/rYVPDQfRcL0
AMD has revealed the Mi 300X chip, which has an industry-leading 192 GB memory capacity, 5.2 TB per second memory bandwidth, and is designed for generative AI. It reduces the number of GPUs required and development time needed for deploying the Mi 300X while accelerating customers' time to market, reducing overall development costs and making deployment effortless. The Mi 300A is currently being sampled while the Mi 300X and eight GPU Instinct platform will begin sampling in Q3, with production expected in Q4 of this year.
Continuous Learning_Startup & Investment
https://youtu.be/ltQ9pbFukUo
Chris Lattner and Lex Fridman discuss the potential of large language models (LLMS) in programming, including their ability to predict and generate code. While LLMS can automate mechanical aspects of coding, it is not a replacement for programmers but a helpful complementary tool. The discussion also covers the potential for LLMS to improve productivity and learn different programming languages. Lattner notes that LLMS can be used for documentation and inspiration, but creating reliable scale systems should focus on algebraic reasoning and creating different nets to implement code rather than expensive LLMS.
Whenever I use an AI product that offers a great user experience, I ask myself: "How the F#🤬 did they do it?"
And if the product is open source, I dive deep into the code, the logic, and of course, the almighty prompt.
Today, I was exploring Bamboo AI, a tool that analyzes data using natural language processing.
Being the curious geek that I am, I dove deep into the prompt to see how it was engineered and to see what types of techniques I could pick up to make my own prompts better.
And in this tweet, I will do my best to reverse engineer the prompt into its building blocks.
Feel free to bookmark this tweet for later reference. I've broken down the prompt into simple pieces for you to replicate if you want.
PS: A (slighlty reduced) snippet of the prompt is attached on the images for reference.
And if the product is open source, I dive deep into the code, the logic, and of course, the almighty prompt.
Today, I was exploring Bamboo AI, a tool that analyzes data using natural language processing.
Being the curious geek that I am, I dove deep into the prompt to see how it was engineered and to see what types of techniques I could pick up to make my own prompts better.
And in this tweet, I will do my best to reverse engineer the prompt into its building blocks.
Feel free to bookmark this tweet for later reference. I've broken down the prompt into simple pieces for you to replicate if you want.
PS: A (slighlty reduced) snippet of the prompt is attached on the images for reference.
Here's what I found:
1. Role
The prompt starts by declaring a clearly defined role for the AI. Most prompts do this, as this has become a standard best practice.
2. Goal
A clearly defined goal on top of the role allows the AI to act in accordance to it. Nothing extraordinary with this prompt until now.
The problem is that most people stop crafting their prompts here, and then wonder why their outputs are useless and random more often than not.
3. Clearly defined input
The prompt clearly states what is the expected input the AI will receive.
This part of the prompt is often overlooked, but I've found it greatly reduces the randomness of the output.
4. Clearly Defined output
Similarly, clearly going over the expected output in minute detail will help steer the model in the exact direction that you want.
This will allow you to pinpoint exactly what it should do, and on top of that, will reduce the need for revisions.
Again, most people never even get to this point and then wonder why the AI never gets them right.
Of course it doesn't; it won't get you right if you haven't told it what to do.
5. Revisions
The prompt clearly states that revisions are to be expected and the output probably won't be the final one.
Once again, clearly stating what can happen during the actual use of this tool.
6. Input example
On top of clearly defining what input to expect, the prompt also shows an input example.
"Show, don't just tell" is a good principle to keep in mind when prompting.
This will greatly reduce the randomness of the model and make for more accurate outputs.
7. Output example
Stating the examples of the output is equally important.
This will allow the model to pick up on the input -> output pattern and make its answers way more relevant, contextual and useful.
See a pattern here?
Clearly state what the AI should do and what to expect.
Don't leave it to chance if you want your outputs to be reliable and useful.
And now that we have reverse engineered how this prompt works, you will hopefully have ideas on how to improve your own prompts.
I sure did.
https://twitter.com/Luc_AI_Insights/status/1668792631806050304?s=20
1. Role
The prompt starts by declaring a clearly defined role for the AI. Most prompts do this, as this has become a standard best practice.
2. Goal
A clearly defined goal on top of the role allows the AI to act in accordance to it. Nothing extraordinary with this prompt until now.
The problem is that most people stop crafting their prompts here, and then wonder why their outputs are useless and random more often than not.
3. Clearly defined input
The prompt clearly states what is the expected input the AI will receive.
This part of the prompt is often overlooked, but I've found it greatly reduces the randomness of the output.
4. Clearly Defined output
Similarly, clearly going over the expected output in minute detail will help steer the model in the exact direction that you want.
This will allow you to pinpoint exactly what it should do, and on top of that, will reduce the need for revisions.
Again, most people never even get to this point and then wonder why the AI never gets them right.
Of course it doesn't; it won't get you right if you haven't told it what to do.
5. Revisions
The prompt clearly states that revisions are to be expected and the output probably won't be the final one.
Once again, clearly stating what can happen during the actual use of this tool.
6. Input example
On top of clearly defining what input to expect, the prompt also shows an input example.
"Show, don't just tell" is a good principle to keep in mind when prompting.
This will greatly reduce the randomness of the model and make for more accurate outputs.
7. Output example
Stating the examples of the output is equally important.
This will allow the model to pick up on the input -> output pattern and make its answers way more relevant, contextual and useful.
See a pattern here?
Clearly state what the AI should do and what to expect.
Don't leave it to chance if you want your outputs to be reliable and useful.
And now that we have reverse engineered how this prompt works, you will hopefully have ideas on how to improve your own prompts.
I sure did.
https://twitter.com/Luc_AI_Insights/status/1668792631806050304?s=20
Twitter
Whenever I use an AI product that offers a great user experience, I ask myself: "How the F#🤬 did they do it?"
And if the product is open source, I dive deep into the code, the logic, and of course, the almighty prompt.
Today, I was exploring Bamboo AI,…
And if the product is open source, I dive deep into the code, the logic, and of course, the almighty prompt.
Today, I was exploring Bamboo AI,…
I'm rlly inspired by ambitious projects that were built fast:
> The Eiffel Tower. (2 yrs)
> Disneyland (366 d)
> Empire State (410 d)
> Javanoscript (10 d)
> iPod (290 d)
> Amazon Prime (42 d)
> Git (17 d)
> Xerox Alto (120 d)
blog post by
@patrickc
: https://patrickcollison.com/fast
https://twitter.com/pwang_szn/status/1668921295457894401?s=20
> The Eiffel Tower. (2 yrs)
> Disneyland (366 d)
> Empire State (410 d)
> Javanoscript (10 d)
> iPod (290 d)
> Amazon Prime (42 d)
> Git (17 d)
> Xerox Alto (120 d)
blog post by
@patrickc
: https://patrickcollison.com/fast
https://twitter.com/pwang_szn/status/1668921295457894401?s=20
Twitter
I'm rlly inspired by ambitious projects that were built fast:
> The Eiffel Tower. (2 yrs)
> Disneyland (366 d)
> Empire State (410 d)
> Javanoscript (10 d)
> iPod (290 d)
> Amazon Prime (42 d)
> Git (17 d)
> Xerox Alto (120 d)
blog post by @patrickc: htt…
> The Eiffel Tower. (2 yrs)
> Disneyland (366 d)
> Empire State (410 d)
> Javanoscript (10 d)
> iPod (290 d)
> Amazon Prime (42 d)
> Git (17 d)
> Xerox Alto (120 d)
blog post by @patrickc: htt…
https://www.nea.com/blog/4-trends-for-ai-startups-and-generative-ai-companies
Key Insights for Preparing AI-Related Service
#1 Generative AI is changing the rules of company building. Generative AI is a new technology that allows machines to create new content, such as images, videos, and text, that is similar to human-generated content. This technology is changing the way companies are built, and entrepreneurs need to be aware of this trend to stay competitive.
#2 Speed is critical in hiring talent for AI startups. The demand for AI talent is high, and startups need to act fast to hire the right people. Instead of relying on recruiters and culture-fit discussions, startups can take a more straightforward approach to hiring talent.
#3AI startups need to focus on solving real-world problems. AI startups should focus on solving real-world problems, such as improving healthcare, transportation, and education. By focusing on these problems, startups can create value for their customers and make a positive impact on society.
#4 Collaboration is key to success in the AI industry. Collaboration between AI startups, established companies, and academic institutions is essential for success in the AI industry. By working together, companies can share knowledge, resources, and expertise to create innovative solutions.
In summary, entrepreneurs who are preparing AI-related services should be aware of the emerging trends in the AI industry. They should focus on solving real-world problems, act fast in hiring talent, and collaborate with other companies and institutions to create innovative solutions. By following these trends, entrepreneurs can stay competitive and create value for their customers.
Key Insights for Preparing AI-Related Service
#1 Generative AI is changing the rules of company building. Generative AI is a new technology that allows machines to create new content, such as images, videos, and text, that is similar to human-generated content. This technology is changing the way companies are built, and entrepreneurs need to be aware of this trend to stay competitive.
#2 Speed is critical in hiring talent for AI startups. The demand for AI talent is high, and startups need to act fast to hire the right people. Instead of relying on recruiters and culture-fit discussions, startups can take a more straightforward approach to hiring talent.
#3AI startups need to focus on solving real-world problems. AI startups should focus on solving real-world problems, such as improving healthcare, transportation, and education. By focusing on these problems, startups can create value for their customers and make a positive impact on society.
#4 Collaboration is key to success in the AI industry. Collaboration between AI startups, established companies, and academic institutions is essential for success in the AI industry. By working together, companies can share knowledge, resources, and expertise to create innovative solutions.
In summary, entrepreneurs who are preparing AI-related services should be aware of the emerging trends in the AI industry. They should focus on solving real-world problems, act fast in hiring talent, and collaborate with other companies and institutions to create innovative solutions. By following these trends, entrepreneurs can stay competitive and create value for their customers.
Nea
4 Trends for AI Startups and Generative AI Companies
(4 EMERGING TRENDS) As generative AI explodes the company-building rules, founders identify trends for AI startups and generative AI companies
Forwarded from BZCF | 비즈까페
https://freebutdeep.substack.com/
최근에 알게 된 뉴스레터중에 재일 재미있게 읽고 있는 뉴스레터인데요. 실제로 만나뵙고 이야기를 나누어봐도 통찰이 가득하신 훌륭하신 분이십니다. 여러 주제를 다뤄주시는데, 많은 분들께 알려지면 좋겠다는 생각들어 조금 뜬금 없지만 공유해봅니다.
최근에 알게 된 뉴스레터중에 재일 재미있게 읽고 있는 뉴스레터인데요. 실제로 만나뵙고 이야기를 나누어봐도 통찰이 가득하신 훌륭하신 분이십니다. 여러 주제를 다뤄주시는데, 많은 분들께 알려지면 좋겠다는 생각들어 조금 뜬금 없지만 공유해봅니다.
Substack
freebutdeep's thoughts (프벗디) | Substack
deal with uncertainties. Click to read freebutdeep's thoughts (프벗디), a Substack publication with hundreds of subscribers.
진입장벽이 무엇입니까? 원천기술이 무엇인가요?
IR 또는 대기업 임원 분들과 미팅 시 가끔 듣는 질문이다.
특히나, 과거 특허나 IP 중심으로 진입장벽을 쌓아오던 시절에 비즈니스 하시는 분들은, 특히 더 많이 질문하는 부분이기도 하다. 나는 과거 BCG 시절 IP 프로젝트도 해봤었기에, 그 질문이 가지는 함의를 나름 잘 이해하고 있기도 하다.
다만, 진입장벽의 정의를, 1) 타사 대비 우리 서비스가 지니는 차별적 경쟁우위, 2) 타사가 진입 못하게 막는, 우리 회사만의 독점적 기술/특허로 정의하는 것은, 현 IT 업에서는 100% 부합하지는 않는다.
미국에서 만난 훌륭한 서비스를 일군 분들의 공통점은, 그 머릿속에 경쟁사 대비 차별적 경쟁우위 & 진입장벽이라는 컨셉이 별로 없다. (적어도 MBA 수업에 오셨던 분들의 이야기를 쭉 들어봤을 때 그렇고, 현지에서 대화하는 분들의 이야기 경청 시 그렇다).
그들의 마음속에 있는 두 가지 키워드는, 유저, 그리고 팀이다. 유저의 만족을 위해 Day 1의 마음으로 더 악착같이 최선을 다하는 것, 그리고 Day 1의 마음으로 움직이는 팀을 더더더 오래 유지하는 것이, 위대한 기업을 일군 창업가들이 공통적으로 강조했던 부분이다. (우버는 초반에 진입장벽이 있었을까? 에어비엔비나 위대한 B2B SaaS 회사들은 그러했을까? 그들이 만든 scale 이 진입장벽일 수 있는데, 그 scale 은 IP 가 아닌 집착과 노력의 시간이 만들어 준 산물이 아닐까? 유저에 대한 집착이 유저를 위한 서비스/기술을 만들어 내고, 그 기술/기능이 흔히 세상이 평가하는 독점적 기술이지는 않을까? 그렇다면 그들의 진입장벽은 결과로 만들어진 독점적 기술일까? 아니면 그 기술을 만들어 낸 팀의 집요함일까? 한 때 훌륭한 기업이, 팀이 무너지는 과정에서 한 순간에 무너지는 것을 보면, market position 을 지켜주는 영원한 기술이 존재하는 것이 맞는가? 그래서 아마존은 Day 1 을 강조하는 것이 아닐까?)
현대 사회에서는 우리 서비스를 좋아해 주는 유저가 많아지는 것이 진입장벽이고 원천기술이다. 유저가 우리 서비스를 좋아해주는 이유는, 우리 회사가 독점적 기술, 차별적 경쟁우위를 가지고 있어서라기 보다는... 다소 부족한 점이 있어도 (버그가 있고, 불편함이 있어도) 유저에게 최선을 다하기 때문이다.
유저에게 최선을 다하는 것이 어렵나? 되물으면, "이 세상에 모든 팀이 유저에게 몇 년 간 꾸준히 진심으로 최선을 다하는 회사가 얼마나 있을까요? 그런 경험 최근에 하신 적 있으실까요?" "지금 귀하의 회사 임직원은 오로지 유저만 바라보며 하루를 집중하고 있나요? 오히려 말씀하시는 분 (예: 임원)의 바를 넘을까를 더 고민하고 있지는 않을까요? 그 과정에서 더 좋은 이직의 기회를 없을까 고민하고 있는 분이 있지는 않을까요?"
요즘은 특허로 기술 사용을 막기 보다는, open API 로 배포하는 시대이다. 경쟁사는 오히려 서로 다른 소구점을 기반으로 함께 업을 키워나가는 나가는 동료인 시대이다. 이런 시대에서의 핵심역량, 차별적 경쟁우위, 진입장벽은, 회사가 정의하는 것이 아닌 유저가 정의해 주시고 이 사회에 정의해 주는 것이다. 그것이 tangible 한가? 오래토록 지속될 수 있는가? 묻는다면, "그래서 팀이 중요하고, 문화가 중요하고, 마음가짐이 중요하고, 사람이 중요요합니다. 그 루프가 무너지면 많은 것이 무너집니다" 라고 말씀드리고 싶다.
사람을 위한 서비스는 사람이 만드는 것이다. 그리고, 사람은 사람을 알아본다.
https://lnkd.in/gDB7Juxr
IR 또는 대기업 임원 분들과 미팅 시 가끔 듣는 질문이다.
특히나, 과거 특허나 IP 중심으로 진입장벽을 쌓아오던 시절에 비즈니스 하시는 분들은, 특히 더 많이 질문하는 부분이기도 하다. 나는 과거 BCG 시절 IP 프로젝트도 해봤었기에, 그 질문이 가지는 함의를 나름 잘 이해하고 있기도 하다.
다만, 진입장벽의 정의를, 1) 타사 대비 우리 서비스가 지니는 차별적 경쟁우위, 2) 타사가 진입 못하게 막는, 우리 회사만의 독점적 기술/특허로 정의하는 것은, 현 IT 업에서는 100% 부합하지는 않는다.
미국에서 만난 훌륭한 서비스를 일군 분들의 공통점은, 그 머릿속에 경쟁사 대비 차별적 경쟁우위 & 진입장벽이라는 컨셉이 별로 없다. (적어도 MBA 수업에 오셨던 분들의 이야기를 쭉 들어봤을 때 그렇고, 현지에서 대화하는 분들의 이야기 경청 시 그렇다).
그들의 마음속에 있는 두 가지 키워드는, 유저, 그리고 팀이다. 유저의 만족을 위해 Day 1의 마음으로 더 악착같이 최선을 다하는 것, 그리고 Day 1의 마음으로 움직이는 팀을 더더더 오래 유지하는 것이, 위대한 기업을 일군 창업가들이 공통적으로 강조했던 부분이다. (우버는 초반에 진입장벽이 있었을까? 에어비엔비나 위대한 B2B SaaS 회사들은 그러했을까? 그들이 만든 scale 이 진입장벽일 수 있는데, 그 scale 은 IP 가 아닌 집착과 노력의 시간이 만들어 준 산물이 아닐까? 유저에 대한 집착이 유저를 위한 서비스/기술을 만들어 내고, 그 기술/기능이 흔히 세상이 평가하는 독점적 기술이지는 않을까? 그렇다면 그들의 진입장벽은 결과로 만들어진 독점적 기술일까? 아니면 그 기술을 만들어 낸 팀의 집요함일까? 한 때 훌륭한 기업이, 팀이 무너지는 과정에서 한 순간에 무너지는 것을 보면, market position 을 지켜주는 영원한 기술이 존재하는 것이 맞는가? 그래서 아마존은 Day 1 을 강조하는 것이 아닐까?)
현대 사회에서는 우리 서비스를 좋아해 주는 유저가 많아지는 것이 진입장벽이고 원천기술이다. 유저가 우리 서비스를 좋아해주는 이유는, 우리 회사가 독점적 기술, 차별적 경쟁우위를 가지고 있어서라기 보다는... 다소 부족한 점이 있어도 (버그가 있고, 불편함이 있어도) 유저에게 최선을 다하기 때문이다.
유저에게 최선을 다하는 것이 어렵나? 되물으면, "이 세상에 모든 팀이 유저에게 몇 년 간 꾸준히 진심으로 최선을 다하는 회사가 얼마나 있을까요? 그런 경험 최근에 하신 적 있으실까요?" "지금 귀하의 회사 임직원은 오로지 유저만 바라보며 하루를 집중하고 있나요? 오히려 말씀하시는 분 (예: 임원)의 바를 넘을까를 더 고민하고 있지는 않을까요? 그 과정에서 더 좋은 이직의 기회를 없을까 고민하고 있는 분이 있지는 않을까요?"
요즘은 특허로 기술 사용을 막기 보다는, open API 로 배포하는 시대이다. 경쟁사는 오히려 서로 다른 소구점을 기반으로 함께 업을 키워나가는 나가는 동료인 시대이다. 이런 시대에서의 핵심역량, 차별적 경쟁우위, 진입장벽은, 회사가 정의하는 것이 아닌 유저가 정의해 주시고 이 사회에 정의해 주는 것이다. 그것이 tangible 한가? 오래토록 지속될 수 있는가? 묻는다면, "그래서 팀이 중요하고, 문화가 중요하고, 마음가짐이 중요하고, 사람이 중요요합니다. 그 루프가 무너지면 많은 것이 무너집니다" 라고 말씀드리고 싶다.
사람을 위한 서비스는 사람이 만드는 것이다. 그리고, 사람은 사람을 알아본다.
https://lnkd.in/gDB7Juxr
Brunch Story
진입장벽? 독점적 기술이 아닌 유저를 향한 태도입니다.
진입장벽이 무엇입니까? 원천기술이 무엇인가요? IR 또는 대기업 임원 분들과 미팅 시 가끔 듣는 질문이다. 특히나, 과거 특허나 IP 중심으로 진입장벽을 쌓아오던 시절에 비즈니스 하시는 분들은, 특히 더 많이 질문하는 부분이기도 하다. 나는 과거 BCG 시절 IP 프로젝트도 해봤었기에, 그 질문이 가지는 함의를 나름 잘 이해하고 있기도 하다. 다만,
Continuous Learning_Startup & Investment
https://m.youtube.com/watch?v=CsruQYKISYI&feature=youtu.be
불확실성 속에서 빠르게 움직이고 방향을 찾아 나서기 위한 10가지 방법 by Jeremy (Co-founder of Rippling and Director of Product Management at Coinbase)
👉(광고) Startup, Investment, Science, Life 등 다양한 주제에 관심이 있다면: https://news.1rj.ru/str/+oonhLBMoVtdjNjI1
1. 폭보다는 깊이: 헨릭슨은 리더가 프레임워크에 의존하기보다는 문제를 깊이 파고들어 해당 분야의 전문가가 될 것을 권장했습니다.
2. 도전적인 MVP 사고방식: 그는 최소기능제품(MVP) 접근 방식이 창의성을 제한하고 잘못된 기술적 결정을 내릴 수 있다고 경고했습니다. 당장 지원되지 않더라도 가장 복잡한 사용 사례를 먼저 설계하면 향후 확장성과 적응성을 확보할 수 있습니다.
3. 소규모 팀을 위한 명확한 미션: 그는 명확한 미션을 가진 소규모 팀은 상황에 맞는 의사결정을 내리고 규모에 맞는 속도를 유지하면서 더 빠르게 대응할 수 있다고 강조했습니다. 이러한 접근 방식은 코인베이스에서 40배 성장하는 동안 그의 재임 기간 동안 중요한 역할을 했습니다.
4. 현장 운영 이해: 헨릭슨은 문제, 과제, 성공을 이해하기 위해 '현장의 팀'과 직접 소통하여 최고 수준의 제품 결정이 현장의 현실과 일치하도록 하는 것이 중요하다는 신념을 공유했습니다.
5. 빠르게 변화하는 문화와 의사 결정: 헨릭슨은 리플링의 문화를 빠른 의사 결정 능력이 요구되는 '속도'의 문화라고 설명했습니다. 이를 위해서는 우선순위와 그렇지 않은 우선순위를 명확히 해야 하며, 이를 통해 모든 사람이 자신의 역량을 최대한 발휘할 수 있어야 합니다.
6. 전문성과 디테일 중심의 접근 방식: 그는 제품 리더가 제품의 세부 사항에 대한 세계적인 전문가가 되어 많은 정보를 흡수하고 불확실성을 탐색하며 의사 결정에 자신감을 가져야 한다고 강조했습니다.
7. 한발 앞서 생각하기: 그는 글로벌 확장을 위한 계획을 생각보다 일찍 세우는 것이 중요하다고 강조했습니다. 모든 국가는 고유한 특성을 가지고 있으므로 미국과 동일한 접근 방식을 적용하는 것은 효과적이지 않을 수 있습니다.
8. 프레임워크와 프로세스: 헨릭슨은 프레임워크가 도움이 될 수 있지만 팀의 특정 라이프사이클에 맞게 조정되어야 한다고 믿습니다. 프로세스에 지나치게 의존하면 제품에 대한 깊은 사고를 방해할 수 있습니다.
9. 채용 철학: 헨릭슨은 제품 관리자를 채용할 때 정신적 민첩성과 통찰력 있는 질문을 중시하며, 큰 비즈니스 그림과 세부적인 질문 모두에 대해 생각할 수 있는 지원자의 중요성을 강조합니다. mental agility and insightful questioning, emphasizing the importance of candidates.
10. 비즈니스 우선순위와 '단호함(Imperatives)': 리플링은 다음 분기 또는 6개월 동안 우선순위가 지정된 업무 목록인 '필수 과제'를 도입했습니다. 이를 통해 개별 팀 목표와 중요한 회사 목표 사이의 균형을 유지할 수 있습니다.
👉(광고) Startup, Investment, Science, Life 등 다양한 주제에 관심이 있다면: https://news.1rj.ru/str/+oonhLBMoVtdjNjI1
1. 폭보다는 깊이: 헨릭슨은 리더가 프레임워크에 의존하기보다는 문제를 깊이 파고들어 해당 분야의 전문가가 될 것을 권장했습니다.
2. 도전적인 MVP 사고방식: 그는 최소기능제품(MVP) 접근 방식이 창의성을 제한하고 잘못된 기술적 결정을 내릴 수 있다고 경고했습니다. 당장 지원되지 않더라도 가장 복잡한 사용 사례를 먼저 설계하면 향후 확장성과 적응성을 확보할 수 있습니다.
3. 소규모 팀을 위한 명확한 미션: 그는 명확한 미션을 가진 소규모 팀은 상황에 맞는 의사결정을 내리고 규모에 맞는 속도를 유지하면서 더 빠르게 대응할 수 있다고 강조했습니다. 이러한 접근 방식은 코인베이스에서 40배 성장하는 동안 그의 재임 기간 동안 중요한 역할을 했습니다.
4. 현장 운영 이해: 헨릭슨은 문제, 과제, 성공을 이해하기 위해 '현장의 팀'과 직접 소통하여 최고 수준의 제품 결정이 현장의 현실과 일치하도록 하는 것이 중요하다는 신념을 공유했습니다.
5. 빠르게 변화하는 문화와 의사 결정: 헨릭슨은 리플링의 문화를 빠른 의사 결정 능력이 요구되는 '속도'의 문화라고 설명했습니다. 이를 위해서는 우선순위와 그렇지 않은 우선순위를 명확히 해야 하며, 이를 통해 모든 사람이 자신의 역량을 최대한 발휘할 수 있어야 합니다.
6. 전문성과 디테일 중심의 접근 방식: 그는 제품 리더가 제품의 세부 사항에 대한 세계적인 전문가가 되어 많은 정보를 흡수하고 불확실성을 탐색하며 의사 결정에 자신감을 가져야 한다고 강조했습니다.
7. 한발 앞서 생각하기: 그는 글로벌 확장을 위한 계획을 생각보다 일찍 세우는 것이 중요하다고 강조했습니다. 모든 국가는 고유한 특성을 가지고 있으므로 미국과 동일한 접근 방식을 적용하는 것은 효과적이지 않을 수 있습니다.
8. 프레임워크와 프로세스: 헨릭슨은 프레임워크가 도움이 될 수 있지만 팀의 특정 라이프사이클에 맞게 조정되어야 한다고 믿습니다. 프로세스에 지나치게 의존하면 제품에 대한 깊은 사고를 방해할 수 있습니다.
9. 채용 철학: 헨릭슨은 제품 관리자를 채용할 때 정신적 민첩성과 통찰력 있는 질문을 중시하며, 큰 비즈니스 그림과 세부적인 질문 모두에 대해 생각할 수 있는 지원자의 중요성을 강조합니다. mental agility and insightful questioning, emphasizing the importance of candidates.
10. 비즈니스 우선순위와 '단호함(Imperatives)': 리플링은 다음 분기 또는 6개월 동안 우선순위가 지정된 업무 목록인 '필수 과제'를 도입했습니다. 이를 통해 개별 팀 목표와 중요한 회사 목표 사이의 균형을 유지할 수 있습니다.
Telegram
Continuous Learning_Startup & Investment
We journey together through the captivating realms of entrepreneurship, investment, life, and technology. This is my chronicle of exploration, where I capture and share the lessons that shape our world. Join us and let's never stop learning!