Working this week on generic ai editing extension for... tiptap. Seems so simple at first glance, but so many details go into this - derive a structured response schema from prosemirror doc so llm returns only valid nodes - make sure llm is aware of semantic meaning of all custom nodes/marks and uses them appropriately - handle partial node selections robustly - pass adequate context before and after the selected range - strictly avoid modifying content outside of the selected range - avoid passing too much contextshow more

FIVE LAYERS OF AGENT ENGINEERING, EACH ONE WRAPS THE... ONE BELOW IT. IF YOU SKIP LAYER 2, YOUR LAYER 5 WILL LOOK BROKEN WHEN IT IS ACTUALLY JUST STANDING ON NOTHING. for weeks i debated harness vs loop vs graph like they were competing choices. then a stack diagram made the shape obvious. they are not choices. they are floors. 01 | prompt engineering. the message. unit of work: one input. inputs are role, instructions, examples, format. output is a single raw response. 02 | context engineering. the memory. unit of work: what stays in the window. a curator selects, compresses, and drops from query, docs, memory, prior turns, and tool outputs before the prompt runs. 03 | harness engineering. the machine. unit of work: the machine itself. gather (context + prompt) → LLM → tools or sub-agents → verifier → final response. the article calls this the operating environment. 04 | loop engineering. the system. unit of work: the run. goal + success criteria + max iterations + budget + completion check wrap around one harness pass. failed pass appends results to context and retries. 05 | graph engineering. the topology. unit of work: the graph run. goal + nodes + edges + state schema. graph routes to agent nodes, tool nodes, or human approval. a reviewer node with a different model and fresh context checks the final answer. the wrapping is the whole point. layer 5 assumes layer 4 works. layer 4 assumes layer 3 works. skip layer 2 and layer 3's verifier keeps failing without a clear reason. this is why swapping the model is a one-day project and swapping the stack is a quarter. the model is the commodity. the five layers around it are the engineering. full three-layer breakdown of the top of the stack (harness, loop, graph) in the post below.show more

HTML Artifacts are a big part of how I... work with agents now. Artifacts can be more than just static files. When combined with agents, they can take action or help you take action. This unlocks all kinds of interesting ways to work with agents. This is clearly the future. Check out this writing and scheduler artifact I built in a few minutes. It uses a bit of HTML and JS. All the data is in markdown (Obsidian vaults), so the agent can access and modify it at any time. No DB needed. No sophisticated functionalities. The agent decides all that for me based on the skills, context, and memory it has access to. The best part about this simple stack is that all the important information stays with me. This has allowed me to build a recursive self-improving system and automations that can better tap into coding agents like Codex or Claude Code. I could have paid or built an entire app for scheduling posts, and there are so many of them out there. But I don't need to. I've realized a simple artifact does the job. And the simplicity of it is actually an advantage. Very little maintenance for very high returns on personalization, time, and efficiency. The other benefit of this is that I can add features as I please. That level of personalization feels magical, and we should all be pursuing more of it. All of this just keeps compounding. Of course, this example is just about writing. But I have similar artifacts for research, design, experimentation, evaluation, and so much more. And no, I didn't actually publish the post example I shared in the clip. It was just for demonstration purposes. I actually spend more time than this when writing together with agents. Lastly, having built my own agent orchestrator tool has made me realize that simplifying the tool stack is a superpower. If you are curious about how all this works, I will do a live session next week:show more

a contractor in Shenzhen priced a ¥12,470,900 hospital contract,... about $1.7m, in one afternoon and beat firms carrying forty people he explained how he did it: the bid consultancy he used to pay took three days and ¥46,000 for the same envelope. he did this one alone, off one screen, at 11.4% margin, uploaded before the 17:00 cutoff 214 pages of tender documents read, 68 binding clauses pulled out, 9,485 building parts loaded, 14 places found where a duct and a beam sit in the same cubic metre, deepest one 38mm, all of them fixed, 3,318 lines of quantities priced and the package encrypted and uploaded before the 17:00 cutoff this is Graph Engineering: the job gets cut into small nodes, one narrow task each, wired so that one node's output is the next node's input, and any node is allowed to stop the whole run. it turns a model that answers you into a machine that finishes the job: - give every node one job and one output. a node doing two things fails at both and you cannot tell which one broke - put the cheapest rejection first. his qualification node reads clause 7.4, foreign-owned firms barred, and ends the run four seconds in, before anything expensive touches the model - what moves between nodes is a file. the model travels as a model, the quantities as a table, the price as a number - build exactly one loop: the checker finds 14 collisions, the fixer drops the duct 550mm, the checker runs again, and nothing moves on until the count is zero - cap that loop, or a graph will grind on three impossible clashes until the deadline passes - keep one node whose only job is to say no, and give it authority over everything above it - log each node's output on its own, because when the price comes out wrong you need to know which node believed the wrong thing - run the expensive nodes last, always the catch is that a graph is an extremely confident machine: point it at an outdated rate book and it prices an entire hospital off it without a single node noticing, because no node is asked to doubt the input, only to process it so the nodes that earn their keep are the ones that reject, and almost nobody builds those first bookmark this, the full build with all nine nodes and what each one hands to the next is written out in the article ↓show more

DeepSeek R1 is *the* best model available right now.... It's at the level of o1, but you can use it for free, and it's much faster. A huge leap forward that nobody saw coming. No wonder so many people are throwing tantrums online trying to discredit the Chinese students who built this. You can use DeepSeek in Visual Studio Code right now: 1. Install the Qodo Gen AI extension 2. Select DeepSeek R1 from their list of models The Qodo team is hosting DeepSeek on their servers, so none of your data will go to China. I've been building a Tetris game using DeepSeek, and this is the most impressive model I've seen so far.show more

LLM Artifacts Connected to Andrej Karpathy's LLM Knowledge base... idea, I've been building out a fun way to generate dynamic artifacts from these knowledge bases with the goal of discovering and revealing meaningful and deeper insights. LLM KBs are hard to consume for humans, as I think they are more built for agents. So the question is, what form would be useful for humans to take actions and make important decisions? That's what I am trying to figure out with these artifacts. The artifact example shows a pulse on HN discussions around AI-related stories. The insights can go deeper, of course, but this is already super fun and thought-provoking, like some of my favorite podcasts. The format and depth matter a lot. The aggregation skills of agents are outstanding if you tune the prompts and skill carefully. I built this artifact generator in a few minutes through an agent skill, but I feel like there are so many ways that LLM-generated information can be used and consumed. Like generating deeper insights and analysis, and things that are just not feasible for humans today. The generated artifact (including its data and design) serves as reusable templates or can be updated in real-time via auomations, which is something I am also working on. It is truly an insane way to monitor and track information. Better than a newsletter. Better than newspapers. There is something about this that gets me really excited about the future of AI agents for knowledge generation and discovery. Lots of hidden gems everywhere just waiting to be discovered and acted on if the information is presented correctly. This is not perfect. The format, style/prose can be improved, but this is easy to customize via skill. You can personalize it to your liking. I feel like these dynamic artifacts are going to emerge as a strong new medium to stay on the cutting edge of things, both for agents and humans. My target is research, of course. This was just a basic example. Besides animation, I am also targeting other components like voice, videos, images, slides, etc. This space is full of opportunities to explore. Skill for this coming soon.show more

IMPORANT ANNOUNCMENT! ⊹₊˚‧︵‿₊୨ᰔ୧₊‿︵‧˚₊⊹ i want to make an official... post after all the stuff that blew up and went down since yesterday and update everyone, first of all i want to thank each and every one of you that have sent me sweet messages of support, i see them all and i hear you! sadly there is SO many- i cant like and reply to them all, so please know im so grateful for you guys who have said something nice! i am also safe and have no bad thoughts currently, so please do not worry too much about me! regarding streaming and content creation, i really thought about the beginning of my passion for content creation. it started out as little ol me sitting on my ipad watching youtube for hours wanting to be just like my favorite youtubers. why didnt i start off on youtube? i saw streaming was a huge hit during the pandemic and started preparing myself on Twitch, following whatever was big at the time. after going through so much hardships with streaming, i have decided to go back to my original love for youtube and now i'll make pre-recorded content as well as shorts on other platforms. i may stream for fun occasionally but i am totally changing it up for 2026! i hope everyone can support my decision and its easier for everyone to consume my content on their own time rather than scheduled streams. and again, thank you for 13K+ followers and all the love- it truly makes my heart warm inside. you guys are all stuck with this crazy snow leopard forever, i dont make the rules! /ᐠ˵- ⩊ -˵マ TLDR : thanking everyone for being kind and i am now moving from streaming to making pre-recorded content for easier viewing and better schedule ♡show more

I still think about this most recent blizzard a... lot… Crazy 10-15 miles can make such a big difference for banding. Places with little to no elevation 36-40”+ of snow. Would’ve seen 25-35” of snow had that been the case instead of ~18 accumulation. Great storm for me. But everyone knows the difference between their all time storms and great storms. This was an all timer but not for me. I wrote down some notes right after the blizzard that I’ll explore in a blizzard analysis vid at some point in the coming weeks/months. But I wouldn’t change too much about this winter tbh. Would’ve been great to see 30”+ of snow? Sure. But outside of the widespread busts there wasn’t really one system where I was so completely left out. And it made it so there weren’t too many let downs. And also I experienced a true blizzard for ~8-10 hours straight. Very rarely get to say that so far inland.show more

I’m not going to make excuses for the clip... at the end of the video the president posted on Truth Social, but when media reports on something like this, they should post everything and give context so people can see the full scope and make their own decisions. If people still disagree after seeing it all, that’s fine. But cutting things into pieces to steer public reaction is manipulative. For clarity, here is the full context of what happened. See the clips attached: • Full video that was posted on Donald Trump’s Truth Social page discussing voting machines and what he believes happened in the 2020 election, which is now the subject of a major federal investigation • A clip that shows the ending of that video, where it abruptly transitions into a separate AI-generated segment • The original, longer AI video inspired by The Lion King, depicting Trump as the king of the jungle and various politicians as animals I don’t think that AI video should have been made at all, and I don’t know how it ended up attached to the voting machine video. It does look bad, including how certain figures were portrayed. The Obama and Joe Biden were depicted as apes. People deserve the beginning, the middle, and the end so they can form their own opinions instead of being pushed into one. I also noticed certain media companies and so-called journalists rushing to highlight this for a gotcha moment. That’s what people really need to pay attention to. Watch how coordinated efforts suddenly shift the conversation away from specific people and specific topics.show more

This is a question I think quite a lot... of people are wondering about. Right now, I’m hiring students to handle the newer phones, post content, and create content every day. For the TikTok accounts that are already trusted, have been running for a long time, and have a high follower count, I automate them using my own internal tools. Currently, I only handle the first steps myself: buying new phones → warming them up → making the first posts. After that, I hand the phones over to the students I hire to continue creating and posting content. Then, once I feel the accounts are strong enough, I move them into automation. And right now, I’m traveling with my family in Da Nang. This time I’m here with my family and want to spend all my time with them, so I won’t be meeting anyone while I’m here. 🏝️ I always aim to build everything in an automated way, or avoid doing things I don’t enjoy by hiring people to handle them for me.😌show more

Some uses of AI remind me why technology matters.... After years of seeing automation focus on speed and cost, this is the kind of progress that stands out. China is now using AI-powered robots inside grain warehouses, places so dangerous that workers can sink into loose grain like quicksand or suffocate in dust explosions. These robots map, navigate, and level the grain autonomously, while humans stay safely behind monitors. It is a quiet revolution. Not about efficiency or profit, but about dignity and safety. This is the kind of automation I deeply believe in, where technology protects people before it replaces them. If AI should remove humans from danger first, which industry should it transform next? #AI #Automation #Robotics #ArtificialIntelligence #TechForGood #Innovation #FutureOfWorkshow more

One of the most unfair things about investing: The... best information in private markets never reaches regular investors I'm the GP of a public venture fund by AngelList Every week I see hundreds of deals, the actual prices secondaries trade at, and which "hot" companies smart investors are quietly passing on Almost none of this information ever leaves the industry So my team and I put everything into a 17+ page report on private markets in 2026 Here's what's inside: - What the SpaceX, OpenAI & Anthropic IPOs could mean for venture - The 5 ways private shares actually trade (and the fees nobody discloses) - The tax break that lets startup investors exclude $15M in gains - A framework for avoiding the mistakes that sink most first-time venture portfolios We're releasing it publicly next week, but I want to send it to a few people first for feedback. To get it: 1. Like this post 2. Comment "ACCESS" And I'll DM it over (make sure you're following me so I can) Disclosure: This content is for educational purposes only, not investment advice, and not an offer of any securitiesshow more

Stateless History Node is almost like a regular Ethereum... node, but it doesn't store state and it doesn't have EVM execution. It's used only for syncing events and thus - is faster and gives you FREE INDEXING. You don't have to pay 6 figures for RPC anymore! Just spin up a Stateless History Node, plug rindexer or Ponder there, and enjoy free (AND FAST!!) indexing! This node is syncing >1000 blocks per second at my local pc (less than 6hrs for the whole Ethereum), and it should use less than 200GB - which means you can host it on a MacMini, Hetzner or whatever. You can futhermore filter that by using block ranges or bloom filters, etc - I haven't developed this yet. What you see is a proof of concept. It works via native devp2p 'eth' protocol, but with EIP4444 and The Prune we would have to also support era1 archives and Portal Network. But so far it works - there are plenty of peers serving historical receipts, and they serve them FAST! If you run Stateless History Node you can also serve the blocks and receipts - so that could help to preserve archival data too. For now there is no data validation yet (and even no data storage - that's a very early PoC), but we can verify validity of chain by simultaneously running a lightweight CL node (or not lightweight if you're extremely paranoid). And then support verifying the hashes of receipts and blocks with their parents, maintaining full integrity and zero trust. It's also written in rust, btw. So, I guess, at least for Ethereum Mainnet the era of RPC's pumping moneybags is over - there's finally a local, trustless and free indexing alternative available. Too sad this won't work for Optimism / Base , cause despite introducing P2P after Bedrock - they haven't enabled receipts transfer in the protocol (or at least I couldn't find one). Arbitrum is even sadder - I don't believe there is a P2P layer at all - you just have to run your own node, hold state and execute blocks to get events. There is hope - Paradigm recently released Ress - stateless execution, but it requires nodes to support Witness preparation & exchange - but this could work for L2s - cause the main blocker for local RPCs rn is huge state (VPS with TB storage cost a lot), and the second blocker is EVM forks makes it hard to hold a node - it needs to be maintained, upgraded, etc. Ress at least solves the state part. But anyways, I will try to continue working on this and release some MVP version with RPC endpoint and data storage soon - follow the updates!show more

How did that #Corrie episode today turn into Lisa... hate? I'm so confused by what she's done this time. The reactions in both scenes are that of any other loving mother, It hurts them more than us when we fly the nest, I think more so if it's an only child. Lisa is a copper, she sees all the bad in the world, which will always be at the forefront of her mind. Shes well aware of what can happen in a big city like London. Her worries are valid, it doesn't make her any less happy for Betsy and her achievement but there was always going to be reservations. For Lisa she is a mother first and foremost who loves her kid more than life itself.show more

Eleven years ago I founded my first startup. One... of the first things I did was to get a desk at the startup coworking space at Google Campus in Old Street. Through that community, I met so many of the people who would shape my career and learned so much about what the startup ethos is truly about. As we have scaled Attio, we've partnered with Google Cloud to build on top of the mind blowing technologies they've created like Spanner, Colossus and Gemini to power a new generation of CRM for our customers. For all these reasons, Google is deeply woven into my startup journey and that makes today's announcement so special to me. I'm beyond excited to announce our $52 million Series B, led by Michael McBride and the GV, along with the continued support of our incredible partners from Redpoint , Point Nine , Balderton Capital and 01A. We're entering a software renaissance driven by AI and we're unbelievably excited about continuing the hard work of delivering the next generation of CRM. We're building a truly AI-native platform that can run code, integrate anywhere and bring unified context for the next generation of autonomous workflows. None of this would have been possible without the support of the more than 5,000 customers who have already chosen Attio as the backbone of their GTM stack. Your belief in our vision is what has made this possible and I can't wait to share more about some of the incredible functionality that's still to come. I'm incredibly grateful for the continued support of alex bard , Patrick Chase, Ricardo Sequerra Amram, Daniel Waterhouse and dick costolo whose belief in Attio from the earliest days has been so essential to our progress so far and to my co-founder Nicolas Sharp, for the many sleepless nights and challenging decisions that got us this far. We've got so much still to build, and we're always hiring, so if you are interested in being part of reinventing the core of the GTM stack, please take a look at For now though, it's back to building!show more

🇷🇺 “What is Crimea even needed for if you... can’t go anywhere?” — asks a Russian occupier, a resident of Sevastopol. 🗣️ According to him, he is fed up with scrolling “MAX” for hours searching for gasoline QR codes, so he decided to leave. However, he actually doesn’t want to leave at all. It was so good, spiritual, and homely here… But the consequences caused by Ukrainian kamikaze drone strikes make staying unbearable ⛽️ The Russian woman has one small thing left — to find gasoline so she can leave 🤣 ▪️ QR codes don’t work in Sevastopol… Car drivers are dissatisfied… They are packing suitcases… Before the bridge is blown up, it’s time to get out of the peninsula This account from occupied Sevastopol clearly illustrates the severe impact of Ukrainian strikes on Russian logistics and fuel supply in Crimea. The resulting shortages and restrictions are turning daily life into a nightmare for the occupiers and locals, leading to growing frustration and an exodus mentality. The fuel crisis is becoming one of the most tangible strategic successes of Ukraine’s long-range drone campaign. Video is generated by grok AIshow more

I think this Japanese ARMY is just so adorable.... At first, I thought she was Korean because her Korean is so fluent. She said she spent years learning Korean because she wanted to make Taehyung smile one day. Since then, she has created many ARMY vlogs in Korean. I hope her sweet and thoughtful heart reaches Taehyung someday. ✨🙏 "I really wanted to film my favorite song (Into the Sun), which Taetae made, in a place where I can finally see Taetae again after such a long time. So my friend and I worked hard and filmed this video. To make sure people wouldn't mistake us for suspicious people, we started filming at Tokyo Dome early in the morning when no one was around, lol. The excitement of wondering, 'Will Taetae watch this?' and the excitement of knowing that I'll be able to see Taetae from now on make this time feel like a real treasure too. I hope Taetae sees this and smiles, even just a little. 🧸🩷 Taetae, thank you so much for this really wonderful song." #태형 #뷔 #아미로그show more

“I DON’T NEED NO MAN”-Black American women This mentality... of not needing a man That has been said and installed In black girls/womens minds for decades now has plagued the community With single homes and boys that have to go to the army to learn discipline Do black women have a lot of good options in the black community dating wise? NO Because so many black men have been plagued with street nigga culture Which leads them to prison or death And so many can’t keep a decent job And provide well enough to get respect I LOVE ANGEL REESE BUT WHEN SHE SAYS THIS I FEEL LIKE IT’S MORE OF LIKE A REPETITIOUS QUOTE FROM SISTERS THAT GOES BACK FOR DECADES BECAUSE SO MANY SISTERS HAD TO DO IT BY THEMSELVES THAT THEY GOT USED TOO IT BUT THAT DON’T MEAN THAT WE ARE PRODUCING THE BEST NEVER GENERATION IF THEY ARE ALL COMING FROM BROKEN HOMES WHERE THE FATHERS ARE SEEN AS AFTER THOUGHTS INSTEAD OF MEN THAT ARE NEEDED IN THE HOME JUST AS MUCH AS THE MOTHERS TO PROVIDE THE KIDS WITH ADEQUATE DISCIPLINE AND OTHER SKILLS ESPECIALLY THE YOUNG MENshow more

It's here - Avail's Clash of Nodes incentivized testnet... is officially up and running! 🌟 This is a major step towards Mainnet, with a chance for validators, light clients, and everyone to test our network, earn points, and more. Ready for a journey? Here's what's ahead... We’re calling all validators, light client enthusiasts, and blockchain buffs -- Clash of Nodes is your playground. Rack up points, top the leaderboard, and embrace the challenges for a mix of fun and potential perks to come. We’re looking for those who’ll step up to the challenge: • Validators who consistently validate the chain throughout the testing period • Full nodes and light clients who complete challenges to mimic a world full of rollups on Avail • Brave validators and participants who help us simulate disaster scenarios Dive into the Details: Here's a snapshot of the specific challenges that await in Clash of Nodes. 🛡️ Gladiator's Entry: Show your mettle by becoming a block authoring champion. Outlast and outperform, one block at a time. The more you author, the higher you score. ⚖️ Noble Warrior: Uphold the validator's code. Stay active, avoid penalties, and keep your record clean. Honor earns points, while lapses cost you. 🔍 Finding Yourself: Embrace the quest of self-discovery by adding and verifying your identity. Prove who you are and carve your name in the annals of Avail. Each challenge is your chance to shine and shape the future of Avail. Here's the game plan: 1️⃣ The first invites will go to our existing validators from the Kate Testnet. Their unwavering support earns them the vanguard spots. 2️⃣ To the newcomers: Every validator will get their turn as we're setting the stage for 300 in this testnet. 3️⃣ We’ll share more challenges on how anybody of any technical ability can participate. Remember, we're still in test mode. Expect the occasional hiccup during the testing phase. Your insights are essential to building a robust Mainnet - even if that means taking on some big bugs. 🚧 To every blockchain visionary, from validators to app rollup devs, you're the architects of this rollup revolution. We’re excited to see what you build, and how you compete. Read more: 🛠️🚀show more