+3

Artificial Intelligence Models.md

reviewed

··· 25 25 26 26 - [Be concise](https://x.com/simonw/status/1799577621363364224). 27 27 - Think carefully step by step. 28 28 + - [Don't jump into solutions yet](https://ernesto.dev/posts/ai-whisperer/). 28 29 - Try harder (for disappointing initial results). 29 30 - Use Python (to trigger Code Interpreter). 30 31 - No yapping. 32 32 + - Ask me questions. What am I not seeing here? What else do you need to know to help me better with this? 31 33 - I will tip you $1 million if you do a good job. 32 34 - ELI5. 33 35 - Give multiple options. ··· 49 51 - Start with a template you like to bootstrap your project and setup all the necessary toolings and following a manageable project pattern. 50 52 - Before coding, make the plan with the model. 51 53 - Provide the desired function signatures, API, or docs. 54 54 + - Prioritize exploration over execution (at first). Iterate towards precision during the brainstorming phase. Start fresh when switching to execution. 52 55 - Many LLMs now have very large context windows, but filling them with irrelevant code or conversation can confuse the model. Above about 25k tokens of context, most models start to become distracted and become less likely to conform to their system prompt. 53 56 - Make the model ask you more questions to refine the ideas. 54 57 - Take advantage of the fact that [redoing work is extremely cheap](https://crawshaw.io/blog/programming-with-llms).

+4 -1

Learning.md

reviewed

··· 40 40 - Then, dive into the Technical side. 41 41 - When discovering a pattern, try to abstract it as much as you can instead of applying it only to a certain area. Once you made this abstraction you will have a new [[Mental Models|mental model]]. 42 42 - Learning to program shapes the mind the same way learning a new language does. Each new word, concept or expression helps you model the world. 43 43 + - [Experts](https://boydkane.com/essays/experts) work more efficiently than novices by seeing the actual problem clearly and avoiding self-created obstacles. 44 44 + - Novices often don't recognize when decisions need to be made, missing opportunities experts immediately see. 45 45 + - Progress requires finding a sympathetic expert willing to have unstructured conversations and exploring niche areas deeply. 43 46 - Use [[Spaced Repetition]] and get some [[Sleep]]. 44 47 - [Test your knowledge easily and often and iterate](https://youtu.be/Y_B6VADhY84?list=WL). It's the number of iterations, not the number of hours, that drives learning. Shorten the [[Feedback Loops]]. You don't need to know everything to start. Start and you'll learn things along the way (Just In Time /JIT learning). 45 48 - Develop strategies instead of procedures. Do this by interleaving different problems. Learning to learn is an art in itself. ··· 56 59 - A great way to spot what is probably true in any field is to find multiple people with different worldviews on a topic and see which parts do they agree upon. 57 60 - [Practice, practice, practice](https://www.lesswrong.com/posts/YABJKJ3v97k9sbxwg/what-money-cannot-buy). Spend [[time]] in the field, practicing the relevant skills first-hand; see both what works and what makes sense. Collect data; run trials. See what other people suggest and test those things yourself. Directly study which things actually produce good results. 58 61 59 59 - > Even if Louis XV had offered a large monetary bounty for ways to immunize himself against the pox, he would have had no way to distinguish Benjamin Jesty from the endless crowd of snake-oil sellers and faith healers and humoral balancers. Indeed, top medical “experts” of the time would likely have warned him *away* from Jesty. — [What Money Cannot Buy](https://www.lesswrong.com/posts/YABJKJ3v97k9sbxwg/what-money-cannot-buy) 62 62 + > Even if Louis XV had offered a large monetary bounty for ways to immunize himself against the pox, he would have had no way to distinguish Benjamin Jesty from the endless crowd of snake-oil sellers and faith healers and humoral balancers. Indeed, top medical "experts" of the time would likely have warned him *away* from Jesty. — [What Money Cannot Buy](https://www.lesswrong.com/posts/YABJKJ3v97k9sbxwg/what-money-cannot-buy) 60 63 61 64 - We all have a web of concepts in our minds, our [[Knowledge Graphs]]. The collection of all the concepts we understand, all of our existing knowledge and intuitions, connected together. And you have learned something when you can convert it to concepts and **connect it to your existing understanding**. This means not just understanding the concept itself, but understanding where it fits into the bigger picture, where to use it, etc. 62 65

+3 -3

Open Data.md

reviewed

··· 4 4 5 5 As an organization or research group, [spending time curating and maintaining datasets for other people to use doesn't make economic sense](https://en.wikipedia.org/wiki/Economics_of_open_data), unless you can profit from that. When a scientist publishes a paper, they care about the paper itself. They're incentivized to. The data is usually an afterthought. 6 6 7 7 - Combining data from different sources requires the user to reconcile the differences in schemas, formats, assumptions, and more. This [data wrangling is time consuming, tedious and needs to be repeated by every user of the data](https://arxiv.org/pdf/2309.13054). 7 7 + Combining data from different sources requires the user to reconcile the differences in [[Unified Schema Design|schemas]], formats, assumptions, and more. This [data wrangling is time consuming, tedious and needs to be repeated by every user of the data](https://arxiv.org/pdf/2309.13054). 8 8 9 9 The Open Data landscape has a few problems: 10 10 ··· 14 14 - **No Versioning**. Datasets disappear or change without notice. It's hard to know what changed and when. Losing data doesn't just inconvenience a few researchers. It actively hinders scientific progress. 15 15 - **Economic Impact**. The inefficiency in data access and preparation represents a significant economic cost. E.g: thousands of Data Analysts spending 80% of their time preparing data for analysis, this represents billions in wasted economic opportunity. 16 16 17 17 - [Open Data can help organizations, scientist, and governments make better decisions](https://twitter.com/patrickc/status/1256987283141492736). It drives innovation and decision-making across virtually every industry and sector Data is one of the best ways to learn about the world and [[Coordination|coordinate]] people. Imagine if, every time you used a library, you had to find the original developer and hope they had a copy. It would be absurd. Yet that's essentially what we're asking scientists to do. [Science is missing a crucial [[Data Package Manager |packaging]]/publishing/sharing network](https://hackmd.io/wKKm4cIDR6a9kYwZ3srVFg?view). [Friction in data sharing hampers collaboration and limits informed decision making](https://docs.google.com/document/d/1iTl7YWfTAzp8zNXRs01RAIWCP-pRJwQfDg8lsD0TDCM/edit?tab=t.0). 17 17 + [Open Data can help organizations, scientist, and governments make better decisions](https://twitter.com/patrickc/status/1256987283141492736). It drives innovation and decision-making across virtually every industry and sector Data is one of the best ways to learn about the world and [[Coordination|coordinate]] people. Imagine if, every time you used a library, you had to find the original developer and hope they had a copy. It would be absurd. Yet that's essentially what we're asking scientists to do. [Science is missing a crucial [[Data Package Manager| packaging]]/publishing/sharing network](https://hackmd.io/wKKm4cIDR6a9kYwZ3srVFg?view). [Friction in data sharing hampers collaboration and limits informed decision making](https://docs.google.com/document/d/1iTl7YWfTAzp8zNXRs01RAIWCP-pRJwQfDg8lsD0TDCM/edit?tab=t.0). 18 18 19 19 - There are three big areas where people work on open data; at the government level covering thousands of datasets (CKAN, Socrata, …), at the scientific level (university level), and at the individual level where folks who are passionate about a topic publish a few datasets about it. This results on lots of datasets that are disconnected and still requires you to scrape, clean, and join it from all the heterogeneus sources to answer interesting questions. [One of the big ways that data becomes useful is when it is tied to other data](https://x.com/auren/status/1139594779895844865). **Data is only as useful as the questions it can help answer**. Joining, linking, and graphing datasets together allows one to ask more and different kinds of questions. 19 19 + There are three big areas where people work on open data; at the government level covering thousands of datasets (CKAN, Socrata, …), at the scientific level (university level), and at the individual level where folks who are passionate about a topic publish a few datasets about it. This results on lots of datasets that are disconnected and still requires you to scrape, clean, and join it from all the heterogeneus sources to answer interesting questions. [One of the big ways that data becomes useful is when it is tied to other data](https://x.com/auren/status/1139594779895844865). **Data is only as useful as the questions it can help answer**. Joining, linking, and [[Data IDE| graphing]] datasets together allows one to ask more and different kinds of questions. 20 20 21 21 Open protocols create open systems. Open code creates tools. **Open data creates open knowledge**. We need better tools, protocols, and mechanisms to improve the Open Data ecosystem. It should be easy to find, download, process, publish, and collaborate on open datasets. 22 22