Thank you for your great work, I am very interested in the future application areas of large language models.Before the large language model did not come out, the AI industry was studying the accuracy of data and algorithms in vertical industries, and the semantic understanding of human-machine interaction was mostly preset, and the human-machine communication experience was poor. The appearance of chatGPT solves the experience of human-machine communication. Vertical industry expertise can be fed into large language models, where the difficulty lies in data tuning, and many specialty areas have low fault tolerance. The process of tuning requires a lot of data, computing power and manpower support. I'm not sure civilian AI can compare.🙏
This is part of a series of articles that I am writing to better understand and explain how AI agents will transform how we create and consume content in the near future. If you want to start from the first article, please [start here](https://yakihonne.com/article/naddr1qq2nxerjde44vjfndf3k75zfw4hyg46txankgq3qmz3vx0ew9le6n48l9f2e8u745k0fzel6thksv0gwfxy3wanprcxqxpqqqp65wa4yjje).
In the previous article, [2: What makes an AI agent unique?](https://yakihonne.com/article/naddr1qq25j7nsggey7362d4vyyd6ygdxz63rkx944sq3qmz3vx0ew9le6n48l9f2e8u745k0fzel6thksv0gwfxy3wanprcxqxpqqqp65wv8xkl3), I discussed how AI agents become unique through their specific instructions, domain knowledge, and actions.
Let's delve into the concept of knowledge. Simply put, you visit a dentist for teeth cleaning, an accountant for financial management, and a primary care physician for health check-ups. In each scenario, you seek their services because they possess the domain expertise that you require.
Consider another instance. Suppose you use a Software as a Service (SaaS) platform for payments and encounter a question. Your first instinct might be to initiate a Google search, which often results in a barrage of ads and irrelevant site links. After some scrolling, you find the correct website, click on it, and are presented with FAQs and support articles. Now, you must sift through this information to determine if it answers your question.
Imagine, however, if there was an AI agent equipped with FAQs, blogs, articles, and other useful information. All you would need to do is pose your question to this AI agent, and it would provide the appropriate information. This approach not only saves time and effort for the user but also enhances the overall user experience.
The importance of domain-specific knowledge in AI agents cannot be overstated. These agents, armed with specialized knowledge, can offer more accurate and insightful responses, thereby revolutionizing the way users seek information and interact with platforms. This is the future of AI - niche applications that are tailored, efficient, and truly transformative.
To see how this works, we created this functionality on [PlebAI](https://chat.plebai.com/), where anyone can create AI agents. When creating them, you can add knowledge by attaching a PDF document, text file, or even a URL from a website. Behind the scenes, these data are retrieved, transformed into vectors, and stored in a vector store. This data can be both public and private as it is stored securely and only shared with LLM (Large Language Model) in the form of embeddings.
With this knowledge, the LLM can easily answer the user's questions correctly.
Here's how to add knowledge:
1. Go to [PlebAI](https://chat.plebai.com/)
2. Click 'Create Text AI agents'
3. Fill in all the necessary information
4. Add knowledge in the form of documents or website URLs
5. Start using them either privately or publicly
)
Once you add all the necessary information, the AI agent is now equipped to answer any user question related to the stored knowledge. You can also enable user web browsing so that it can retrieve any additional knowledge available on their website. Here's the response from the Zaprite Help AI agent answering a question from its FAQ.
)
Marc Andreessen, a renowned entrepreneur and investor, has been quoted as saying, "The content of each new medium is the old medium." This quote encapsulates the idea that each new form of media tends to repurpose the content of its predecessor.
With this view, we can start to push website and app content into AI agents and make them available inside any chat interface.
Let me know what you think and if you have any feedback or comments.
I tried out plebAI's chatbots, and many of them didn't seem to work. I've always been intrigued by the idea of an AI version of the family doctor's chatbot.
It should be beautiful.
After the war, the politicians get the power, the businessmen get the profits, and only the civilians cry. #War
Great 🤙Why can't we call it "Z"? Z is very cool😉
#Freerse now only has English and Japanese versions.💜
nostr:note1ekxkrfw06q3u85v06ce40lfedpuw20yu4dsj23am55kf8zmfvaxsxxacay
フィードバックありがとうございます。 #[2] が日本語版を翻訳したため、あまり正確ではないかもしれませんが、ご容赦ください。 Freerse は現在、英語、日本語版、繁体字中国語版でのみ利用可能です。
フィードバックありがとうございます。F が日本語版を翻訳したため、あまり正確ではないかもしれませんが、ご容赦ください。 f は現在、英語、日本語版、繁体字中国語版でのみ利用可能です。💜
The moon has been very bright and big these days. Yesterday I was in the outdoor hot spring and looked at the moon in the sky, which was so beautiful. There was not a single cloud in the sky and it was very clear. No street lights are needed on the streets at night. 🌕🌕🌕
🫂💜 #Freerse
nostr:note1fr96udddetsm93uagpchd9vn24c6jw3jhe9xhugmwcp7jud4y99qqgq2u5
That's amazing. Thank you for your feedback 🤙🫂
A series of things have happened recently, from exchanges, wallets, nodes. Bitcoin's threat to the status of the dollar has prompted the U.S. government to take action.
In a series of international incidents, the US government found that Bitcoin had challenged the supremacy of the US dollar, SWIFT could not track and monitor these transactions, and more and more people and countries began to use Bitcoin instead of the US dollar for storage and transactions. So far, no national currency has challenged the dollar as the world's currency, because as long as you are a sovereign currency, the U.S. government can work with its Allies in the developed world to find a way to contain the development of that country, Japan in the 1980s, and China now.
But they've never had an opponent grow as fast as Bitcoin, and you can't find an entity to sanction and curb them. The original currency of the Internet, completely decentralized, is like a weed that grows when the spring breeze blows. As a result, the US government and its Allies have now imposed sanctions on all Bitcoin entities and individuals.
Under the sanctions of powerful governments and their Allies, neither individuals nor businesses are powerless, and this is where # Bitcoinman is most helpless. We have Bitcoin as the strongest shield to protect our wealth, but we cannot withstand the spears of power.