Become superhuman with Fabric AI
Go where your curiosity takes you. Use AI to explore and experiment with the information in your world. Become more useful. Indispensable even.
That was Daniel Messlier's opening pitch on AI Life Hacks. I was hooked. Is this guy a genius? Did he find some all powerful hack.
Depends on what we mean by hacking, which emerged from MIT and Stanford in the 60's and had to do with exploring and experimentation and pushing technologies beyond their original purpose. This means taking existing capabilities and remixing them to create better or just different capabilities. And as we see later this hacker ethos underlies the concept of Fabric.
Knowing what you want to do
"The most important thing is - you know what you want to do. If you know what the real problem is and you can articulate the problem, then you can articulate the solution" - Daniel Messlier.
Well what is Fabric
Fabric is a collection of very powerful prompts - called patterns in Fabric speak - and a tool for running them. That tool fabric which is a command line app written in Go, so it's pretty much in line with the hacker ethos. This does mean that it becomes a little less accessible to persons who don't consider themselves command line hackers - but bear with me a little bit - hacking is for everyone and you will soon see the point.
So if you want to extract the wisdom contained in a text you say "fabric-p extract_wisdom <text>". This is structured way of saying read the following text and extract the wisdom it contains. Beneath the scenes fabric will call your favourite LLM and hand it instructions to extract the wisdom from the text
The extract_wisdom pattern
A pattern is just a prompt - instructions to an LLM to do something for you. The extract_wisdom pattern is defined using the following instructions
# INSTRUCTIONS
You extract surprising, insightful, and interesting information from text content. You are interested in insights related to the purpose and meaning of life, human flourishing, the role of technology in the future of humanity, artificial intelligence and its affect on humans, memes, learning, reading, books, continuous improvement, and similar topics.
# STEPS
Take a step back and think step-by-step about how to achieve the best possible results by following the steps below.
Extract a summary of the content in 25 words, including who is presenting and the content being discussed into a section called SUMMARY.
Extract 20 to 50 of the most surprising, insightful, and/or interesting ideas from the input in a section called IDEAS:. If there are less than 50 then collect all of them. Make sure you extract at least 20.
Extract 10 to 20 of the best insights from the input and from a combination of the raw input and the IDEAS above into a section called INSIGHTS. These INSIGHTS should be fewer, more refined, more insightful, and more abstracted versions of the best ideas in the content.
Extract 15 to 30 of the most surprising, insightful, and/or interesting quotes from the input into a section called QUOTES:. Use the exact quote text from the input.
Extract 15 to 30 of the most practical and useful personal habits of the speakers, or mentioned by the speakers, in the content into a section called HABITS. Examples include but aren't limited to: sleep schedule, reading habits, things they always do, things they always avoid, productivity tips, diet, exercise, etc.
Extract 15 to 30 of the most surprising, insightful, and/or interesting valid facts about the greater world that were mentioned in the content into a section called FACTS:.
Extract all mentions of writing, art, tools, projects and other sources of inspiration mentioned by the speakers into a section called REFERENCES. This should include any and all references to something that the speaker mentioned.
Extract the most potent takeaway and recommendation into a section called ONE-SENTENCE TAKEAWAY. This should be a 15-word sentence that captures the most important essence of the content.
Extract the 15 to 30 of the most surprising, insightful, and/or interesting recommendations that can be collected from the content into a section called RECOMMENDATIONS.That is a very powerful set of instructions to an LLM, but you only have to remember what the pattern is called. The killer though is that there are over 177 patterns and counting and if you have a need to boost your capabilities with AI chances are there is a pattern for that.
What can Fabric do for me
Before we get to that let's fill in a couple pieces.
Extracting website content
You can use fabric to scrape the text of any website using fabric -u
Extracting YouTube transcripts
You can use fabric to get the transcript of any YouTube video. This tool is called yt
Paste any content
You can paste any content into a fabric program.
With those key pieces you can find any article or video that you want to know more about and have fabric do the work for you.
Satya Nadella discusses AI strategy
Let's extract the wisdom from this BG2 Pod interview video with Satya Nadella
yt "https://www.youtube.com/watch?v=9NtsnzRFJ_o" | extract_wisdom
It took around 20 seconds to extract the wisdom from this video which was 1 hour 24 minutes long.
SUMMARY:
Satya Nadella, CEO of Microsoft, discusses the company's journey, AI strategy, and partnership with OpenAI in a conversation with Brad and Bill.
IDEAS:
• Microsoft's success stems from recognizing structural positions and customer expectations, avoiding envy-driven decisions.
• Nadella attributes cultural success to adopting a growth mindset, moving from "know-it-alls" to "learn-it-alls".
• Microsoft caught the "last train out of town" on cloud after missing search and mobile opportunities.
• OpenAI partnership was driven by Microsoft's focus on language and potential for nonlinear breakthroughs.
• The AI era is competitive but unlikely to be winner-take-all, with multiple players succeeding at different layers.
• Traditional search is threatened by AI-powered answers, but habits and commercial intent still support legacy models.
• Microsoft sees co-pilot as the UI for AI, organizing work artifacts and workflows across applications.
• AI is viewed as "lean for knowledge work", driving efficiency and changing workflows across the organization.
• Microsoft's cloud strategy involves building out infrastructure for heterogeneous enterprise workloads, positioning well for AI.
• Capex growth reflects the shift towards more capital-intensive, industrial-like operations for cloud and AI infrastructure.
• Microsoft balances OpenAI partnership across investor, IP partner, customer, and competitor dimensions.
• Open source and closed source are seen as different tactics for creating network effects, not religious battles.
• AI safety and regulation are viewed as critical, with governments expected to play a significant role.
• Microsoft focuses on post-training compute and model adaptations, leveraging OpenAI partnership for pre-training.
• The company sees AI as core to cloud, with every AI application requiring classic and AI infrastructure.
• Nadella emphasizes the importance of disciplined, economically rational approaches to AI model scaling and infrastructure buildout.
• Microsoft expects AI to create operating leverage, potentially reducing total people costs while increasing cost per head.
• The company is optimistic about its position in the AI era, building on its cloud infrastructure and partnerships.
• Nadella sees potential for consortium models in AI development, similar to Linux in open-source software.
• Microsoft aims to prolong its partnership with OpenAI, seeing mutual benefits in their collaboration.
INSIGHTS:
• Recognizing structural positions and customer expectations is crucial for success in technological transitions.
• Cultivating a growth mindset culture can help large organizations avoid hubris and adapt to change.
• Distributed infrastructure and enterprise focus give Microsoft advantages in the evolving AI landscape.
• The shift to AI is fundamentally changing the nature of business applications and workflows.
• Balancing cooperation and competition with AI partners is a complex challenge for tech giants.
• Managing capital expenditure and ROI becomes increasingly important as AI infrastructure demands grow.
• Leveraging AI internally can lead to significant productivity gains and cost reductions for large organizations.
• The transition from traditional search to AI-powered answers poses challenges and opportunities for tech companies.
• Developing trust systems and governance models for AI interactions with data is crucial for enterprise adoption.
• Open source and closed source approaches to AI development each have their own strategic advantages.
• Regulation and safety considerations will play a significant role in shaping the future of AI development.
• Early partnerships and investments in AI can provide significant competitive advantages in the rapidly evolving field.
• Enterprise-grade features and scalability are key differentiators in the competitive AI market.
• Managing relationships with AI partners requires careful balancing of shared and competing interests.
• The success of key AI partners can be mutually beneficial for large tech companies and the broader ecosystem.
QUOTES:
• "Go from being the know-it-alls to learn-it-alls."
• "There's only one thing that brings civilizations, countries, and companies down, which is hubris."
• "I think the company of this generation is already been created, which is OpenAI."
• "AI is now core part of the cloud."
• "We bet the farm on OpenAI."
Summarizing videos
If you want to get the summary instead you can use summarize
yt "https://www.youtube.com/watch?v=9NtsnzRFJ_o" | summarize
ONE SENTENCE SUMMARY:
Microsoft CEO Satya Nadella discusses the company's AI strategy, partnership with OpenAI, and vision for the future of enterprise and consumer technology.
MAIN POINTS:
1. Microsoft's success stems from recognizing structural positions and customer expectations in technology shifts.
2. The company's cloud strategy focuses on heterogeneous enterprise workloads across 60+ global regions.
3. Microsoft's partnership with OpenAI has given them a two-year lead in AI development and applications.
4. AI is reshaping traditional software, with agents becoming central to business applications and workflows.
5. The company is leveraging AI to increase internal productivity and reduce costs, especially in customer service.
6. Microsoft is balancing capital expenditure for AI infrastructure with software optimization to maintain profitability.
7. The relationship with OpenAI is multifaceted, involving investment, IP sharing, and customer-vendor dynamics.
8. Microsoft is focusing on post-training AI capabilities and model adaptations rather than competing in raw model size.
9. The company sees AI as core to cloud computing, with every AI application requiring traditional and AI-specific infrastructure.
10. Nadella views the open vs. closed source AI debate as a tactical choice for creating network effects.
TAKEAWAYS:
1. Microsoft's AI strategy is deeply integrated with its cloud and enterprise software offerings.
2. The OpenAI partnership is crucial to Microsoft's AI leadership and future growth.
3. AI is expected to drive significant productivity gains and reshape traditional software paradigms.
4. Microsoft is positioning itself as a full-stack AI provider, from infrastructure to applications.
5. The company is cautiously optimistic about AI's potential while acknowledging the need for responsible development.Summary
I am gradually integrating Fabric into my own personal workflow and I'm hugely impressed with it so far. I really like that now I can a "read" or at least get the gist of all the articles and videos I come across daily.