if you’re talking about AI / machine learning and haven’t read the works of Hofstadter, you’re missing the big human picture

This is insane

watching your agents with ratatui and merits galactic terminal ratatui.rs/ github.com/lofimichael/merit…

I didn’t build anything flashy with Fable Instead, I had it audit all my current and past projects, github repos, and hundreds of personal journals It spat out a -giant- playbook for places I’ve historically failed and areas I’ve undeniably 100% succeeded in over and over This playbook is something I now can use repeatable over and over to come back to, and lesser models can use it with ease, even now that Fable 5 is pulled Ask stronger questions with stronger models, ask them to create durable documents and findings - this compounds and you will not go wrong

Great article about the future of Robotics and AI by @lofimichael It matches my belief and hope that we won't live in a black mirror episode but rather a balanced and exciting future. cellularthinking.com/p/50-bi…

👏 NO 👏 MORE 👏 PLAINTEXT 👏 SECRETS 👏 1,250 packages secured in @AutomicVault.

Tools you rely on should not be constantly trying to sell you things 💯

Last week, I taught an AI agent how to (preliminarily) play Final Fantasy Tactics Advance - a GBA game that is completely obfuscated and inaccessible. No clean APIs, no standard interface, entirely bytecode/application memory-driven. cellularthinking.com/p/advan… I don’t think it’s an understatement to say: the moat around all closed software is rapidly closing. (Not mentioned in the article: the usage of Ghidra, an NSA toolkit, to reverse-engineer the app)

Introducing TheClaw.gg - Every Discord server is now an AI Agent API We're talking millions of messages to be used for personal agents and flows theclaw.gg

Alrighty! This took me a fair moment to spin up and harden, but I'm finally ready to release it! TheClaw.gg creates API access for any given Discord server it's installed in, public or private with tailored controls/limits/permissions (i.e. license key/subscription gates) for everyone in it - perfect for agents. What I'd love and my ask: give it a try, run some queries with it, please give me your feedback ( DM me bug reports if any or join the support discord), let me know how it can be useful for you your community! theclaw.gg/

impending release, stay very tuned

M5 Max looking insane - at ~600GB/s bandwidth, this implies an M5 Ultra will have ~1.2TB/s unified memory bandwidth Combine that with 512GB of RAM, local models are eating so good apple.com/newsroom/2026/03/a…

When the Anthropic API returns 403s

if you've ever played RTS games and you're not using peon ping you're losing out on the training your brain has unconsciously done

This one is so good I had to print a sticker of it

Very interested in what the coming era of highly bespoke software might look like. Example from this morning - I've become a bit loosy goosy with my cardio recently so I decided to do a more srs, regimented experiment to try to lower my Resting Heart Rate from 50 -> 45, over experiment duration of 8 weeks. The primary way to do this is to aspire to a certain sum total minute goals in Zone 2 cardio and 1 HIIT/week. 1 hour later I vibe coded this super custom dashboard for this very specific experiment that shows me how I'm tracking. Claude had to reverse engineer the Woodway treadmill cloud API to pull raw data, process, filter, debug it and create a web UI frontend to track the experiment. It wasn't a fully smooth experience and I had to notice and ask to fix bugs e.g. it screwed up metric vs. imperial system units and it screwed up on the calendar matching up days to dates etc. But I still feel like the overall direction is clear: 1) There will never be (and shouldn't be) a specific app on the app store for this kind of thing. I shouldn't have to look for, download and use some kind of a "Cardio experiment tracker", when this thing is ~300 lines of code that an LLM agent will give you in seconds. The idea of an "app store" of a long tail of discrete set of apps you choose from feels somehow wrong and outdated when LLM agents can improvise the app on the spot and just for you. 2) Second, the industry has to reconfigure into a set of services of sensors and actuators with agent native ergonomics. My Woodway treadmill is a sensor - it turns physical state into digital knowledge. It shouldn't maintain some human-readable frontend and my LLM agent shouldn't have to reverse engineer it, it should be an API/CLI easily usable by my agent. I'm a little bit disappointed (and my timelines are correspondingly slower) with how slowly this progression is happening in the industry overall. 99% of products/services still don't have an AI-native CLI yet. 99% of products/services maintain .html/.css docs like I won't immediately look for how to copy paste the whole thing to my agent to get something done. They give you a list of instructions on a webpage to open this or that url and click here or there to do a thing. In 2026. What am I a computer? You do it. Or have my agent do it. So anyway today I am impressed that this random thing took 1 hour (it would have been ~10 hours 2 years ago). But what excites me more is thinking through how this really should have been 1 minute tops. What has to be in place so that it would be 1 minute? So that I could simply say "Hi can you help me track my cardio over the next 8 weeks", and after a very brief Q&A the app would be up. The AI would already have a lot personal context, it would gather the extra needed data, it would reference and search related skill libraries, and maintain all my little apps/automations. TLDR the "app store" of a set of discrete apps that you choose from is an increasingly outdated concept all by itself. The future are services of AI-native sensors & actuators orchestrated via LLM glue into highly custom, ephemeral apps. It's just not here yet.

Any time a successful response comes into my worker I’m having it play this clip

Maximize for the consistent long game and you -will- win

the #biohacking channel is full of gems eventually i think we'll publish a "the tinkerer way" book together 😂

I’VE BEEN SAYING THIS FOR YEARS

we keep cooking, we stay winning