Wal

@NoPriorsPodcast" target="_blank" rel="nofollow noopener">youtube.com/@NoPriorsPodca… github.com/karpathy/autor… karpathy.github.io/2026/02/12/mic…

AI is the most powerful amplifier of human capability ever built. Amplifiers don't close gaps. They widen them.

Building a multi-agent system 𝗶𝘀𝗻'𝘁 𝗷𝘂𝘀𝘁 𝗮𝗱𝗱𝗶𝗻𝗴 𝗺𝗼𝗿𝗲 𝗮𝗴𝗲𝗻𝘁𝘀 (This is why specialized agents beat generalists every time) Instead of a single agent trying to handle everything, 𝗠𝘂𝗹𝘁𝗶-𝗮𝗴𝗲𝗻𝘁 𝘀𝘆𝘀𝘁𝗲𝗺𝘀 employ teams of specialized agents, each with its own focused task. So for example, you could have a team of: A 𝗣𝗹𝗮𝗻𝗻𝗶𝗻𝗴 𝗔𝗴𝗲𝗻𝘁 that decides how to handle the users request. A 𝗤𝘂𝗲𝗿𝘆 𝗥𝗲𝘄𝗿𝗶𝘁𝗶𝗻𝗴 𝗔𝗴𝗲𝗻𝘁 that takes messy user queries and decomposes them into more manageable, clear subqueries. A 𝗥𝗲𝘁𝗿𝗶𝗲𝘃𝗮𝗹 𝗔𝗴𝗲𝗻𝘁 𝗮𝗻𝗱/𝗼𝗿 𝗗𝗮𝘁𝗮 𝗦𝗼𝘂𝗿𝗰𝗲 𝗦𝗲𝗹𝗲𝗰𝘁𝗼𝗿 that specializes in finding the right information from the right source. A 𝗧𝗼𝗼𝗹 𝗥𝗼𝘂𝘁𝗶𝗻𝗴 𝗔𝗴𝗲𝗻𝘁 that decides which tools to use and when. A 𝗔𝗻𝘀𝘄𝗲𝗿 𝗔𝗴𝗲𝗻𝘁 that decides how to best combine all the results to provide the more complete answer to the user. 𝗠𝗲𝗺𝗼𝗿𝘆 is what allows an agentic system like this to work. Short-term memory tracks the current conversation and recent actions. Long-term memory stores patterns, successful strategies, and domain knowledge. When agents share memory, they build on each other's work instead of starting from scratch every time. Each agent has access to specific tools. The retrieval agents can call different search APIs. The validation agent might use a scoring model. The synthesis agent has access to the LLM for generation. They don't all need every tool - they just need the right ones for their specialized task. IMHO, this is way more robust than a single agent trying to handle everything. When retrieval fails, the coordinator can try a different retrieval agent. When validation catches low-quality results, it can trigger a re-retrieval with different parameters. Specialization means better error handling and more reliable outcomes. More agents means more complexity. But for complex tasks, multi-agent systems consistently outperform single agents trying to do it all.

"We’re flying wherever we want. Nobody is even shooting at us." Donald Trump, on the same day Iran shoots down an F-35 fighter jet.

The EU calls it euphemistically "settler violence". These Israeli figures are much blunter: "horrific ethnic cleansing of Palestinians" with active support of IDF officials & police. Signatories include former Likud & Kadima ministers, Netanyahu's former natsac advisor, etc.

On this day 2 years ago, the israelis were massacring civilians in #Gaza; 2 years on & they’re inflicting the same on Lebanon & Iran | @QudsNen

Israel used the excuse of a declaration of national emergency to justify this blatant suppression of religious rights. Further belying Israel's claim that it respects freedom of religion. 2/2

During the holiest time of the year for Christians (Easter) and Muslims (Ramadan), Israel has completely blocked the Old City: no stores, no tourists, no worshipers at Al Aqsa or Church of the Holy Sepulcher. No one. For the first time in decades, if not ever. 1/2

@r0l0pes @trq212 youtu.be/CEvIs9y1uog

@trq212 ?

CC Livestream x.com/i/broadcasts/1…

AI AGENTS 101 (58 minute free masterclass) send this to anyone who wants to understand ai agents, claude skills, md files, how to get the most out of AI etc in plain english: 1. chat vs agents - chat models answer questions in a back and forth while agents take a goal, figure out the steps, and deliver a result 2. agents don’t stop after one response. they keep running until the task is actually finishedno babysitting required 3. everything runs on a loop. they gather context, decide what to do, take an action, then repeat until done 4. the loop is the system. they look at files, tools, and the internet. decide the next step. execute and then feed that back into the next step. over and over until completion 5. the model is just one piece. gpt, claude, gemini are the reasoning layer. the key is model + loop + tools + context 6. mcp is how agents use tools. it connects things like browser, code, apis, and your internal software. once connected, the agent decides when to use them to get the job done 7. context beats prompt all day. you don't need to write perfect prompts. load your agent with context about your business, style, and goals and then simple instructions work 8. claude.md or agents.md is the onboarding doc it tells the agent who it is, how to behave, what it knows, and what tools it can use. this gets loaded every time before it starts 9. memory.md is how it improves. agents don’t remember by default. this file stores preferences, corrections, and patterns you tell the agent to update it, and it gets better over time 10. skills + harnesses make it usable. skills are reusable tasks like writing, research, analysis the harness is the environment like claude code or openclaw that runs everything. basiclaly, different interfaces, same system underneath this episode with remy on @startupideaspod was one of the clearest ways of understanding a lot of the core concepts of ai agents could be the best beginners course for ai agents 58 mins. all free. no advertisers. i just want to see you build cool stuff. im rooting for you. send to a friend watch

I'm going to be doing a skills livestream tomorrow, Thursday March 19th @ 11:30am PT to talk live about skills and how to use them. Come with questions! Special guest @hudaman from Uber to share how Uber is using skills.

Stop sleeping on AI Obsidian + Claude Code = your own JARVIS. Takes 1 hour to build. Most people will scroll past this and stay unproductive. The ones who stop and build it will never work the same way again.

Wow my frontend-slides skill now has 10k stars on GitHub So many people have turned this into their default way of making slides Bye powerpoint

Fixed it for you @Reuters.

The sneaker shop lady revealed an easy trick to tie shoelaces that won't slip open. 👟

French journalist Marine Vlahovic was found dead in her home in Marseille while working on a documentary covering Israel's genocidal war against the Palestinians in the Gaza Strip.

Today I'm releasing my entire newsletter archive (350+ posts) and all podcast transcripts (300+ episodes) as AI-friendly Markdown files. Plus an MCP server and GitHub repo. A few months ago I shared my podcast transcripts on a whim, and y'all built the most amazing things—an RPG game, a parenting wisdom site, infographics, a Twitter bot, and 50+ other projects. Let's see what happens when I give you even more data. Grab the data here: LennysData.com. Paid subscribers get all of the data (some 350 posts and 300 transcripts). Free subscribers get a subset. I don’t think anyone’s ever done anything like this before, and I’m excited to give you this excuse to play with that AI tool you've been meaning to try. Here’s my challenge to you: build something, and let me know about it. I’ll pick my favorite and give you a free 1-year subscription to the newsletter. Just post a link to your project in the comments here: lennysnewsletter.com/p/how-i-built-…. If you’ve already built something, slurp in this new data and submit it, too. I’ll pick a winner on April 15th. Check out today's newsletter post for inspiration on what you could to build: lennysnewsletter.com/p/how-i-built-… LFG.

Un 18 de marzo de 1962, el imperialismo francés era derrotado y se veía obligado a firmar los Acuerdos de Evian en Argelia, tras una guerra de exterminio colonial contra el pueblo argelino por su independencia, donde asesinó a más de un millón de personas. El Frente de Liberación Nacional argelino logró la claudicación de un colonialismo francés, que ya había perdido toda legitimidad internacional, y que se vio obligado a aceptar un alto el fuego, un referéndum de autodeterminación y la liberación de los presos politicos con una amnistía general.... aunque Francia nunca reconoció sus crímenes y tardó décadas en ni siquiera reconocer el término "guerra" contra Argelia. Fue una de las guerras de liberación nacional más crueles de la descolonización africana, aunque tras 132 años de opresión imperialista, finalmente el pueblo argelino logró la expulsión de alrededor de un millón de colonos europeos originarios de Francia, Italia o España. La guerra de liberación nacional que hoy se da en Palestina debe acabar igual, los colonos deben volver a Europa y se debe terminar con el apartheid racista.

Context Engineering is quickly becoming a must-have skill for 𝗔𝗜 𝗘𝗻𝗴𝗶𝗻𝗲𝗲𝗿𝘀 𝗶𝗻 𝟮𝟬𝟮𝟲. And over the past year, it has evolved quite a bit. That’s exactly why I’m hosting a free live workshop this Friday. We’ll break down what’s actually changing right now - and what you need to understand to stay ahead. In this session, you’ll learn: 👉 The core patterns defining context engineering in 2026 👉 Key trade-offs between different context management strategies 👉 How to apply these patterns to build more effective agentic systems Whether you’re building LLM-powered apps or scaling AI systems, this is knowledge you’ll want at your fingertips. 🗓 Friday, March 20th | 6 PM (GMT+2) Save your spot here: maven.com/p/0bd8ae/state… Looking forward to seeing you there!

Repo: github.com/sgoudelis/grou… If you want more practical AI gems and use cases, join our free newsletter with daily tutorials and latest news in AI: simplifyingai.co