Thecriptomoneda

@karpathy ⁰p

Farzapedia, personal wikipedia of Farza, good example following my Wiki LLM tweet. I really like this approach to personalization in a number of ways, compared to "status quo" of an AI that allegedly gets better the more you use it or something: 1. Explicit. The memory artifact is explicit and navigable (the wiki), you can see exactly what the AI does and does not know and you can inspect and manage this artifact, even if you don't do the direct text writing (the LLM does). The knowledge of you is not implicit and unknown, it's explicit and viewable. 2. Yours. Your data is yours, on your local computer, it's not in some particular AI provider's system without the ability to extract it. You're in control of your information. 3. File over app. The memory here is a simple collection of files in universal formats (images, markdown). This means the data is interoperable: you can use a very large collection of tools/CLIs or whatever you want over this information because it's just files. The agents can apply the entire Unix toolkit over them. They can natively read and understand them. Any kind of data can be imported into files as input, and any kind of interface can be used to view them as the output. E.g. you can use Obsidian to view them or vibe code something of your own. Search "File over app" for an article on this philosophy. 4. BYOAI. You can use whatever AI you want to "plug into" this information - Claude, Codex, OpenCode, whatever. You can even think about taking an open source AI and finetuning it on your wiki - in principle, this AI could "know" you in its weights, not just attend over your data. So this approach to personalization puts *you* in full control. The data is yours. In Universal formats. Explicit and inspectable. Use whatever AI you want over it, keep the AI companies on their toes! :) Certainly this is not the simplest way to get an AI to know you - it does require you to manage file directories and so on, but agents also make it quite simple and they can help you a lot. I imagine a number of products might come out to make this all easier, but imo "agent proficiency" is a CORE SKILL of the 21st century. These are extremely powerful tools - they speak English and they do all the computer stuff for you. Try this opportunity to play with one.

Claude prompts for frontend development github.com/mustafakendigu…

¡Nuevo curso gratuito de Anthropic! Agent Skills paso a paso, desde cero ✓ Crear una skill y buenas prácticas ✓ Diferencias con Tools y MCP ✓ Para Claude Code y Visual Studio Code 2 horas de contenido y 10 vídeos → deeplearning.ai/short-courses/…

Installs Anthropic skills into AI coding agents github.com/numman-ali/ope…

🦜🔗 Just finished @langchain's LangSmith Essentials Course! Check it out here: academy.langchain.com

@ShreyaYadav___ Prompt

¡Acabo de completar Mastering Generative AI: Agents with RAG and LangChain con @edXOnline! edx.org/course/masteri…

Check out Tiptap Pagination - Add pagination to your Tiptap editor! romikmakavana.me/tiptap-paginat…

Announcing a significant upgrade to Agentic Document Extraction! LandingAI's new DPT (Document Pre-trained Transformer) accurately extracts even from complex docs. For example, from large, complex tables, which is important for many finance and healthcare applications. And a new SDK makes using it require only 3 simple lines of code. Please see the video for technical details. I hope this unlocks a lot of value from the "dark data" currently stuck in PDF files, and that you'll build something cool with this!

Copy and Paste These ChatGPT Prompts to Learn Anything 10x Faster👇

also, here is one part that people not interested in the rest of the post might still be interested in:

Vibe coding isn't going away. It's only getting better, more powerful, and more popular. 🚀 A directory of the 29 top vibe coding tools real builders are using today (bookmark this thread):

Even though I’m a much better Python than JavaScript developer, with AI assistance, I’ve been writing a lot of JavaScript code recently. AI-assisted coding, including vibe coding, is making specific programming languages less important, even though learning one is still helpful to make sure you understand the key concepts. This is helping many developers write code in languages we’re not familiar with, which lets us get code working in many more contexts! My background is in machine learning engineering and back-end development, but AI-assisted coding is making it easy for me to build front-end systems (the part of a website or app that users interact with) using JavaScript (JS) or TypeScript (TS), languages that I am weak in. Generative AI is making syntax less important, so we can all simultaneously be Python, JS, TS, C++, Java, and even Cobol developers. Perhaps one day, instead of being “Python developers" or “C++ developers,” many more of us will just be “developers”! But understanding the concepts behind different languages is still important. That’s why learning at least one language like Python still offers a great foundation for prompting LLMs to generate code in Python and other languages. If you move from one programming language to another that carries out similar tasks but with different syntax — say, from JS to TS, or C++ to Java, or Rust to Go — once you’ve learned the first set of concepts, you’ll know a lot of the concepts needed to prompt an LLM to code in the second language. (Although TensorFlow and PyTorch are not programming languages, learning the concepts of deep learning behind TensorFlow will also make it much easier to get an LLM to write PyTorch code for you, and vice versa!) In addition, you’ll be able to understand much of the generated code (perhaps with a little LLM assistance). Different programming languages reflect different views of how to organize computation, and understanding the concepts is still important. For example, someone who does not understand arrays, dictionaries, caches, and memory will be less effective at getting an LLM to write code in most languages. Similarly, a Python developer who moves toward doing more front-end programming with JS would benefit from learning the concepts behind front-end systems. For example, if you want an LLM to build a front end using the React framework, it will benefit you to understand how React breaks front ends into reusable UI components, and how it updates the DOM data structure that determines what web pages look like. This lets you prompt the LLM much more precisely, and helps you understand how to fix issues if something goes wrong. Similarly, if you want an LLM to help you write code in CUDA or ROCm, it helps to understand how GPUs organize compute and memory. Just as people who are fluent in multiple human languages can communicate more easily with other people, LLMs are making it easier for developers to build systems in multiple contexts. If you haven’t already done so, I encourage you to try having an LLM write some code in a language you’d like to learn but perhaps haven’t yet gotten around to, and see if it helps you get some new applications to work. [Original text: deeplearning.ai/the-batch/issu… ]

Something fun: AI Avatar of me built, by DeepLearning.AI and @realavatarai. Video has details. This is a work in progress, but please come chat with me in avatar form, and let me know what you think! deeplearning.ai/avatar Thank you Jeff Daniel @consciouspilot and team for working with us on this!

Stop copy pasting from ChatGPT ChatGPT’s writing style is terrible and unimpressive. Here's a hack to train ChatGPT to write exactly like you.

The hottest new programming language is English

@gdb Are You the next?

I have deep appreciation for what each of Barret, Bob, and Mira brought to OpenAI. We worked together for many years, and we are all members of the team that helped make OpenAI what it is today. They each brought something different to the table. A personal anecdote about each: Mira and I first worked together closely on the GPT-3 API, which was the first product OpenAI created. It was probably the hardest project I’ve done, since (as one of our researchers remarked) it wasn’t clear if anyone would pay for GPT-3. Together with Peter Welinder, we would be on the phone at 5p every day, partly supporting each other and partly strategizing on what needed to happen the next day. I am grateful for her leadership and her hard work and contributions to OpenAI over the years. Bob’s first project at OpenAI was the robotic hand. He initially came in to learn a little bit about deep learning, and ended up staying to manage research for many years. I worked closely with Bob on many aspects of our organization. He has been a thought partner for me, where we would dive deep together into whatever question lay before us and find a way through. Barret and his close collaborators had been thinking about starting a startup, but joined us to help build what we called at the time a “superassistant” out of GPT-4. This project morphed into ChatGPT. I found it very rewarding watching him grow as a leader within OpenAI over these years — I often remarked to him that it’s felt like he’s been here forever even though he joined “only” 2 years ago. There is no way around the sadness of also closing the chapter that has brought us to this point. But, when I look to the future, I’m very excited about the potential of our research organization with Mark leading it. The mission is not yet done, and there’s so much left to build together — advancing capability, safety, and positive impact on the world.

@ElPutoPueblo @Laura_Herrera @luiscrh @DIANColombia @MincomercioCo creditos a la ia que uso

Es muy probable que @luiscrh deje la @DIANColombia y pase a ser el nuevo @MincomercioCo. Parece que es cuestión de unos días.

@ylecun This GPT-2 test is a secret test for something much bigger to come.

One might think that, by now, people would realize that retrieving the solution to a common puzzle does not require any reasoning ability.