I made this for Sentry Hackweek. I'll be doing... a deep dive soon, but it's a personal recorder that sends my transcripts to a router that determines if the text is a simply a todo, reminder OR if it's work. If it's work, Pi agents get started in it right away, coding or just doing research. Built using: ESP32-S3: 1100mAh Battery: for all agent work for deterministic workflows, automations to help design the case + a ton of sandpaper to get it smooth. Also a adafruit mic on thereshow 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

Robyn is a personal AI platform that lets you... build AI agents to do actual work for you. Need a market analysis, an investor deck, meeting prep, or a weekly briefing? Just describe what you need in plain English, and Robyn builds an agent that uses your context and connected apps to get it done. You get finished work, not just answers. You can even schedule agents to run automatically or share them with others. Basically, an entire team of AI agents that knows you and works for you. This is the future of AI. Try it here:show more

Dynamic workflows are a generalization of harnesses, automations, loops,... routing, and graphs. It's the most powerful feature I have built into my agent orchestrator. Supports all kinds of patterns that leverage different agent backends (claude, codex, pi, hermes,...). It's a meta-harness approach that unlocks new forms of test-time compute. Example of use cases it supports: > LLM councils to get different perspectives from LLMs or plan more intensively > Dynamically routing tasks to different agents based on needs (e.g., cost efficiency and optimal intelligence) > Advisor/Judge + executor workflows and pretty much any complex graph-based pattern required by the task. I find it especially useful for long-running work and code reviewing. > Agent teams that talk to each other if needed for the task. I like to use this for AI editing, artifact creation, and other creative tasks. And I am sure it supports so many things that I haven't discovered yet. I got inspired by the dynamic workflow feature released by the Claude Code team. I had actually built it earlier this year but wanted to generalize it across different agent backends. I think this is going to become more popular in the coming days. I will share more of my findings soon.show more

I'm working on a mod for the excellent Dungeons... of Eternity that lets you and your friends play as your VRChat avatars! Still a lot of work to be done (no other mods exist for this game) but if there's interest I'll put alpha builds on my Patreon, and will release it for free when it's readyshow more

If you own a tree business doing $2M to... $5M in revenue, I want to pay for 30 minutes of your time. I’m 20 years old and on track to hit $1M in revenue with my land clearing business in 2026. I’ve started the process of bringing on a certified arborist to help me expand into residential tree work in 2027. I started climbing when I was 14 and worked for a few tree companies before I started clearing land. I'm so pumped to get back into tree work and have a ton of questions. DM or comment if you’re open to a Zoom. I’m happy to pay whatever rate you think is fair.show more

I had a great experience with WGU and I’m... considering doing a second masters there just for my own personal enrichment. if you already have work experience a WGU degree will give you that on paper credential that you need to get past hiring blocks for me I didn’t accelerate the program. I read every piece of material and it truly gave me everything I needed to be able to do my job in a new career. #wgu #cheatcode #collegeboundshow more

Good Saturday to all. 🌞 God bless Elon for... all the work he's doing for humanity, including that Tesla Roadster. It's a thing of beauty. Stay locked in but not like this, and have a fantastic day!!! 🤣😭show more

I made a tool It's for sharing images with... coding agents in envs where copy/paste doesn't work (e.g. terminals over ssh) It gives you ready-to-go prompts, or you can copy as OCRshow more

What's a meta-agent? It's an agent that manages other... agents mid-task. It can intervene, rewind, fork & audit them as they work – think "git for agents". It's also the emerging layer between you & your agents, a new interface for human-AI interaction! Here's what it unlocks🧵show more

$PONS officially made me a millionaire. the tears are... literally coming to my eyes. it's crazy how quickly life can change, sometimes i think it was just luck. but that would take away from all the work i've put in to get here. starting september with over $1m in my account still feels like a dream, but it's real. i love this world, and i love myself for never giving up.show more

The things I admit, JUST KIDDING 🤣 ...also, this... is a reminder that it's okay to laugh today, even if life isn't going okay. Hope this made you smile, if even for a moment 😊 🍋 #fun #funny #silly #goofy #laughshow more

Increasingly, HTML Artifacts are becoming a core part of... how I work with AI agents. Long-horizon agent sessions need a better way to surface insights about what work it has done. This may not be obvious right now, but as you start to let your agent work on dynamic workflows, large codebases, long-running loops (e.g., using /goal), and deep research tasks, you need a good way to present results. Chat window is not it. You also don't want to just trust everything the agents do. Artifacts help provide an important verification layer, which in turn enables important decision-making. I like HTML artifacts because I can just ask the agent to produce as many of them (and in whatever form) as I need to verify the work and make sense out of everything. I even built a nice tab system for my artifacts. They are great for continual learning and research. I use HTML artifacts for logging, tracking experiments, brainstorming, managing my inbox, code reviews, agent session management, deep research, writing, reading, and so much more. I believe Andrej Karpathy wrote about this somewhere: As we move on to more advanced applications of AI agents and outputs get more complex, we will start to find the need for even more advanced forms of interactions with AI, including interactive neural videos/simulations.show more

I'm hoping that the damage to MCP's reputation gets... undone this year Being able to dynamically get input from the user for subtool calls is incredible, and since it's a standard any agent that implements it gets to work with thisshow more

I’ve been MIA lately cause I was in a... car accident, my car is totaled and some minor injuries. I’m currently not able to work for a bit so I started a gofundme to help during this time and get a new car. If you want to donate or share the link is below 🫶🏽show more

If it was a man doing this to a... little girl, everyone (including men) on Twitter would be calling for his arrest. Women get away with a lot of stuff in this country. A LOT.show more

I love this new battery dock for Apple Vision... Pro. It's a game changer if you use Mac Virtual Display. It gives the battery a dedicated home, makes it really easy to connect to power, and lets me jump between work and other visionOS experiences. Link below.show more

I just built my own wiki generator plugin for... my agents. My agents can now generate wikis for anything I ask. One of my favorite wikis is called PaperWiki. This is a great example of what Andrej Karpathy describes. It uses obsidian vaults to organize papers, retrieve LLM-generated summaries, diagrams, and other advanced views for paper exploration. When Obsidian UI is not enough, I use my own artifact generator inside my agent orchestrator (see clip for example). This allows my agents to build any kind of view or exploration feature that I need. The papers are all curated with automations and several rules/patterns I have manually built over the years. On the surface, this looks basic. But behind the scenes, there are advanced search capabilities, connections, metadata, derived data, and other interesting bits of information that are extremely useful for my research agents. This is mostly built for agents. The artifact preview is just a high-level way to validate and quickly assess the quality of the wiki, suggest improvements, and it's also great for research. I use tobi lutke's qmd for all search capabilities. Everything is markdown. The summaries and even the diagrams. The wiki updates on its own based on several automations I have optimized over the past couple of weeks. The wiki grows and self-improves based on several requirements important for my research use cases. This is as personalized as it gets. There is nothing like it out there. And I use my research expertise to continue improving it over time. This is a vanilla wiki. There are so many things I want to build on top of this. Different aggregations, views, artifacts, etc. All to help automate more of my research work and accelerate productivity. I think the biggest leverage here is how powerful this could be for discovery and experimentation. One of my goals is to use it to find deeper connections and insights that would otherwise elude the top human researchers and use those to generate interesting new hypotheses and research experiments. That way, my agents can use autoresearch to explore research ideas at the frontier. Stay tuned for more.show more

Miguel Angel Jiménez has one of the smoothest, most... unhurried, and most effective golf swings ever put on display. Never a care in the world. He simply swings from the inside, lets it work over the top, and then strolls away from aces like he's competing in a Macarena contest. The beauty of Jiménez's motion isn't just that it works—it's that it's built to last. If you'd like to learn the classic over-the-top swing that's stood the test of time, check out my Classic OTT instructional video. Learn to swing with rhythm, freedom, and a move you can trust for a lifetime. For lessons or information, email: [email protected] #GolfSwing #MiguelAngelJimenez #ClassicSwing #GolfInstruction #OverTheTopSwing #GolfTipsshow more