implementation
Key insight: Building an audience is an act of service, not self-promotion. Find a way to educate or entertain (or both).
nathanbarry.com • The Audience Shortcut: How the Right People Paying Attention Changes Everything
Summarization: Given a large amount of text, the model generates a summary of the main points. Paraphrasing: Given a text, the model generates a rephrasing of the text in its own words.
Arsath Natheem S • Chatgpt Book for Beginners
He encourages questioning what you read and taking the other side, even if you (or anyone you are around) doesn’t believe it. This isn’t to be contrarian for the sake of it but instead to push yourself into a friction-filled point of view outside of the bubble you may be in.
every.to • Sailing Against the Current of Frictionless AI
This all may sound highly unnatural, but I promise that, even if it is the most ambiguous step, intervention selection is surprisingly intuitive. Most of your nonconscious brain is busily chunking away on precisely these kinds of trade-offs all the time: we pair complementary flavors in cooking, triangulate location/cost/proximity to our favorite
... See moreMatt Wallaert • Start at the End: How to Build Products That Create Change
.implementation
- Essences vs. sequences
In a pre-AI world, whether you were building software or teams, or writing books or marketing plans, you needed to strip the problems you were facing down to their bare elements—their essence—and work your way forward from there. In building software, you need to define your core user and the problem you want to solve; in
... See moreDan Shipper • Five New Thinking Styles for Working With Thinking Machines
Impact of AI on Problem-Solving Methodologies: Artificial Intelligence (AI) has significantly transformed problem-solving methodologies across various fields, enhancing analytical capabilities and decision-making processes. By leveraging machine learning algorithms and data analysis, AI can identify patterns and generate insights that humans may overlook, leading to more efficient and effective solutions. Furthermore, AI tools facilitate collaboration among teams, enabling them to approach complex challenges with a combination of human creativity and computational power.
This creates what economists call a moral hazard in both directions. Vendors paid per "completed task" face incentives to use cheaper models, minimize compute, skip quality checks, and classify ambiguous outcomes as successes. Customers face incentives to overload systems with low-value tasks or dispute outcomes to avoid
payment. You've rebuilt the
... See moreEvan Armstrong • Don’t Sell the Work
(using memory methods), and then review to keep it ready in your mind for new learning.
Kevin Horsley • Unlimited Memory: How to Use Advanced Learning Strategies to Learn Faster, Remember More and be More Productive
• Instructions / System Prompt: An initial set of instructions that define the behavior of the model during a conversation, can/should include examples, rules ….
• User Prompt: Immediate task or question from the user.
• State / History (short-term Memory): The current conversation, including user and model responses that have led to this moment.
•
Philipp Schmid • The New Skill in AI Is Not Prompting, It's Context Engineering
Context engineering components and definitions
Likewise, had he linked it to his existing knowledge base—in other words, instead of moving a fresh box or folder into his attic, had he integrated it into an existing, related one, be it on the topic of bloody crime scenes with bloodless bodies,
Maria Konnikova • Mastermind
.implementation