NSDT工具推荐: Three.js AI纹理开发包 - YOLO合成数据生成器 - GLTF/GLB在线编辑 - 3D模型格式在线转换 - 可编程3D场景编辑器 - REVIT导出3D模型插件 - 3D模型语义搜索引擎 - AI模型在线查看 - Three.js虚拟轴心开发包 - 3D模型在线减面 - STL模型在线切割 - 3D道路快速建模
谷歌最近刚刚在其 AI Studio 上向公众发布了 Gemini 1.5 Pro。Gemini Pro 1.5 拥有 1,000,000 个多模态 token 上下文大小。这比 Claude 2.1 (200k) 和 GPT4-turbo (128k) 等现有模型有了巨大的飞跃
为了测试模型从其长上下文中检索内容的能力,我们使用了needle-in-a-haystack(大海捞针)测试。
1、Gemini 1.5 Pro简介
Gemini 1.5 pro 的召回率达到 99.7% 以上,甚至高达 10M 个 token!
除了推理长文档和复杂代码库之外,我发现最有趣的是它分析和推理视频的能力。
在他们的演示中,他们向模型输入了 Buster Keaton 的 45 分钟无声电影“Sherlock Jr.”。并使用每秒一帧的速度,将其转换为 684k 个标记的输入上下文。
该模型可以回答相当复杂的问题(见下文)
你可以在此处观看完整的演示视频。
这开辟了很多可能性。
例如,Simon Willison 有创意地拍摄了一段 7 秒的书架视频,Gemini 能够返回书名和作者的 JSON 数组。
鉴于此,我想亲自测试一下。
2、让Gemin看视频
这段视频在我的稍后观看列表中已经有一段时间了,我想为什么不使用 Gemini 来回答“如何构建一个可扩展到公司的产品?”这个问题?
在我获得这个视频的mp4后,我前往Google AI Studio。
我使用视频标签上传了视频。
一开始它给我一个错误“视频太长”,所以我不得不把它缩短到 59 分 59 秒。我又试了一次,大约 5 分钟后,它就上传了。
它包含了高达 946,800 个 token!
3、让Gemini回答有关视频的问题
根据 OpenAI 的计算,100 个 token ~= 75 个单词,总计 710,100 个单词。
因此,在快速浏览完视频后,我针对几个问题进行了测试。
3.1 What is the rule of 40/20/20?
我首先给出一个简短的提示,要求它返回答案的时间戳,以便我可以核实它们。
The rule of 40/20/20 is a financial metric used to measure the health of software-as-a-service (SaaS) companies. It states that a company’s combined revenue growth rate and profit margin should be equal to or greater than 40%. Additionally, the rule suggests that sales and marketing expenses should be around 20% of revenue, while research and development and general and administrative expenses should each be around 20% of revenue.
The speaker discusses the rule of 40/20/20 at the following timestamps: 09:04–09:14.
我们来检查一下 09:04 是否提到了这条规则。
果然如此!
继续下一个。
3.2 What is the minimum viable segment?
回答如下:
The minimum viable segment is the smallest group of customers that you can dominate with your product. This group should have the same needs, pain points, budget, product use case, and customer profile. By focusing on this small group, you can quickly learn what works and what doesn’t, and then iterate on your product to make it even better. Once you have dominated this segment, you can then expand to other segments with similar needs.
The speaker discusses the minimum viable segment at the following timestamps: 19:44–20:05 and 31:27–31:34.
太棒了!回答中的两个时间点都提到了这个术语!
3.3 How to check on your value proposition?
回答如下:
To check on your value proposition, you need to ask yourself the following questions:
- Is it “BLAC” and white? BLAC stands for Blatant, Latent, Aspirational, and Critical. Blatant needs are obvious and painful, and customers are actively looking for solutions. Latent needs are not as obvious, but they are still important. Aspirational needs are things that customers would like to have, but they are not essential. Critical needs are essential to the customer’s business or personal life.
1. Is it simple to use and install? Customers should be able to easily understand how to use your product and get it up and running quickly.
2. Is it low to no initial cost? Customers should not have to pay a lot of money upfront to try your product.
3. Does it provide instant and ongoing value? Customers should see the value of your product immediately and continue to see value over time.
4. Does it play well in the ecosystem? Your product should work well with other products and services that your customers are already using.
The speaker discusses how to check on your value proposition at the following timestamps: 13:09–13:33.
3.4 Why would a VC say no to your product? ❌
回答如下:
There are a number of reasons why a VC might say no to your product. Some of the most common reasons include:
- The market is too small. VCs are looking for companies that have the potential to grow into large, billion-dollar businesses. If your target market is too small, it will be difficult to achieve that kind of scale.
- The problem you are solving is not valuable enough. VCs want to invest in companies that are solving big, important problems. If the problem you are solving is not valuable enough, customers will not be willing to pay for your product.
- Your product is not differentiated enough. There are a lot of companies out there competing for VC dollars. If your product is not differentiated enough, it will be difficult to stand out from the crowd.
- Your team is not strong enough. VCs invest in people as much as they invest in ideas. If your team does not have the experience and expertise to execute on your vision, VCs will be hesitant to invest.
The speaker discusses why a VC might say no to your product at the following timestamps: 38:10–38:44.
我原本以为它会在 25:48 左右提到一些事情,其中一名学生提到 VC 可能会说“不”,以及你如何将其视为对公司的价值判断。但我想这个问题一开始就很模糊。
但第 38:10–38:44 段没有提到任何关于 VC 说“不”的事情。
3.5 List down all the questions asked in this talk and what the speaker responded as a suggestion/solution ❌
回答如下:
Here are all the questions that were asked by the audience in this talk, along with the speaker’s suggestions/solutions:
Question 1: How can you make your product simple to install? (41:45)
Speaker’s suggestion: There are a number of ways to make your product simple to install, such as:
- Making it self-service. This means that customers should be able to install and use your product without any help from your team.
- Providing clear and concise documentation. This documentation should walk customers through the installation process step-by-step.
- Offering a free trial or demo. This allows customers to try your product before they buy it, which can help to reduce their perceived risk.
Question 2: What is one gain your product can offer to provide instant value? (53:29)
Speaker’s suggestion: To provide instant value, your product should solve a critical need for your customer. This means that your product should help them to:
- Increase revenue
- Reduce costs
- Save time
- Reduce risk
- Gain a competitive advantage
If your product can do one or more of these things, customers will see the value of it immediately and be more likely to buy it.
Question 3: How do you find product-market fit? (54:31)
Speaker’s suggestion: Finding product-market fit is a process of iteration and experimentation. You need to start with a small group of target customers and get their feedback on your product. Then, you need to use that feedback to improve your product and make it more valuable to your target market. This process can take time, but it is essential for building a successful company.
Question 4: How do you know when you have product-market fit? (58:51)
Speaker’s suggestion: There is no single metric that can tell you definitively whether or not you have product-market fit. However, there are a few signs that you can look for, such as:
- Customers are using your product and getting value from it.
- Customers are willing to pay for your product.
- Your product is growing organically through word-of-mouth.
If you are seeing these signs, it is a good indication that you are on the right track to finding product-market fit.
问题 1 和 2 是视频中的真实问题,但问题 3 和 4 不是。它也错过了讲座中的其余问题。
3.6 Did the speaker say anything about how to name your product? ❌
回答如下:
Yes, the speaker briefly mentioned how to name your product at timestamp 33:07. He said that the name of your product should be:
- Memorable
- Easy to spell and pronounce
- Descriptive of what your product does
He also said that it is important to make sure that the domain name for your product is available.
所以这是一个幻觉答案,我到了 33:07,演讲者根本没有提到这一点。
3.7 Provide a detailed summary for this lecture.
回答如下:
This lecture is about how to build a product that scales into a company. The speaker, Chris Gardner, is a partner at Underscore VC, a venture capital firm that invests in early-stage startups.
Gardner begins by talking about the “product-company gap.” This is the gap between having a great product and having a great company. Many startups fail because they focus too much on their product and not enough on the other aspects of building a successful company, such as go-to-market strategy, business model, and team.
Gardner then talks about how to design for “product-go-to-market fit.” This means making sure that your product is solving a valuable problem for a specific target market, and that you have a way to reach those customers and convince them to buy your product. He suggests starting with a “minimum viable segment,” which is the smallest group of customers that you can dominate with your product. By focusing on this small group, you can quickly learn what works and what doesn’t, and then iterate on your product to make it even better.
Gardner also shares two “startup secrets” for building a product that scales into a company:
1. Friction-free products that SLIP: This stands for Simple to install and use, Low to no initial cost, Instant and ongoing value, and Plays well in the ecosystem. By designing your product to meet these criteria, you can make it easier for customers to try, adopt, and deploy your product, which can lead to faster growth and lower customer acquisition costs.
2. Co-create a win-win via strategic partnerships: By partnering with other companies, you can leverage their resources and reach to get your product in front of more customers. This can be a great way to accelerate your growth and build a lasting company.
Gardner concludes by emphasizing the importance of focusing on your core value and providing proof of value to your customers. Don’t just tell customers that your product is valuable, show them. Use data and metrics to demonstrate the impact that your product can have on their business or personal life.
By following these lessons, you can increase your chances of building a product that scales into a lasting company.
3.8 Provide a glossary of all the terms mentioned in the video that is worth knowing and remembering.
回答如下:
Here is a glossary of terms mentioned in the video that are worth knowing and remembering:
- Product-company gap: The gap between having a great product and having a great company.
- Product-go-to-market fit: Making sure that your product is solving a valuable problem for a specific target market, and that you have a way to reach those customers and convince them to buy your product.
- Minimum viable segment (MVS): The smallest group of customers that you can dominate with your product.
- Friction-free products that SLIP: Products that are Simple to install and use, Low to no initial cost, provide Instant and ongoing value, and Play well in the ecosystem.
- Product-led growth (PLG): A go-to-market strategy that relies on the product itself to drive customer acquisition and growth.
- Whole product: The complete solution that your customer needs, including your product, complementary products and services from partners, and customer support.
- BLAC: An acronym that stands for Blatant, Latent, Aspirational, and Critical. It is used to qualify customer needs.
- Blatant need: An obvious and painful need that customers are actively looking for solutions for.
- Latent need: A need that is not as obvious, but is still important.
- Aspirational need: A need that customers would like to have, but is not essential.
- Critical need: A need that is essential to the customer’s business or personal life.
- Customer acquisition cost (CAC): The cost of acquiring a new customer.
- Freemium: A business model that offers a basic version of a product for free, but charges for premium features.
3.9 What are all the important lessons mentioned?
回答如下:
Here are some of the important lessons mentioned in the video:
- It’s not just about the product. While having a great product is important, it’s not the only thing that matters. You also need to have a strong go-to-market strategy, a solid business model, and a great team.
- Design for product-go-to-market fit. This means making sure that your product is solving a valuable problem for a specific target market, and that you have a way to reach those customers and convince them to buy your product.
- Make your product friction-free. This means making it simple to install and use, low to no initial cost, and providing instant and ongoing value.
- Co-create a win-win via strategic partnerships. By partnering with other companies, you can leverage their resources and reach to get your product in front of more customers.
- Focus on your core value. Don’t try to be everything to everyone. Focus on the one thing that your product does better than anyone else, and make sure that your messaging and positioning are clear and consistent.
- Provide proof of value. Don’t just tell customers that your product is valuable, show them. Use data and metrics to demonstrate the impact that your product can have on their business or personal life.
By following these lessons, you can increase your chances of building a product that scales into a lasting company.
3.10 What are 10 questions I should ask myself when scaling my product into a company?
回答如下:
Based on the video, here are 10 questions you should ask yourself when scaling your product into a company:
Product-Market Fit
1. What is the core value proposition of my product?
2. What is the minimum viable segment (MVS) for my product?
3. Have I achieved product-market fit with my MVS?
4. How can I make my product more friction-free (SLIP)?
Business Model
5. What is my business model?
6. How will I price and package my product for different customer segments
7. How will I distribute my product and capture value?
Go-to-Market Strategy
8. What is my go-to-market strategy?
9. How will I position, message, and communicate my product to my target market?
10. What channels will I use to distribute my product and reach my target market?
By asking yourself these questions, you can develop a clear and comprehensive strategy for scaling your product into a successful company
4、结束语
看起来,问题不太具体、不太明确,很容易让人产生幻觉。
提示可以解决这个问题。
但另一方面,仅仅因为视频中没有这些信息并不意味着它没用,尤其是对于“为什么风险投资家会说不”这个问题。
所以,作为一个总结和学习 YouTube 视频的工具,我认为它仍然是一个很好的工具。
原文链接:I used AI to watch an hour-long lecture
BimAnt翻译整理,转载请标明出处