Milos Zuffa

@GamewithDave Dyna Blaster Multiplayer

For anyone who used a computer between 1990 & 2005… what’s the one game you still think about?

@exQUIZitely Norton Commander since the 8086 Intel IBM PC. Mostly just to go to the GAMES folder and run games such as Dyna Blaster, Duke Nukem and Lotus racing 😂

This one is for the OGs. Norton Commander or PC Tools - which was your #1?

@SimonDecio @ritu_twts Same for me

as a dev, what was your first code editor?

@ritu_twts ZX Spectrum BASIC, then QuickBasic in DOS, then TurboPascal

@and_coder @aditiitwt My youth

@aditiitwt This old...

You may be old But are you this old

@aditiitwt Norton Commander?

@jpreagan @karpathy Soon Apple should begin supporting adding your claws as family members :-)

@karpathy andrej, wouldn't recommend giving it your personal apple id if that's what you mean by giving your private data/keys separate account for the bot and bring in your data on a case by case you'll need separate account if you want to text it via imessage x.com/jpreagan/statu…

Bought a new Mac mini to properly tinker with claws over the weekend. The apple store person told me they are selling like hotcakes and everyone is confused :) I'm definitely a bit sus'd to run OpenClaw specifically - giving my private data/keys to 400K lines of vibe coded monster that is being actively attacked at scale is not very appealing at all. Already seeing reports of exposed instances, RCE vulnerabilities, supply chain poisoning, malicious or compromised skills in the registry, it feels like a complete wild west and a security nightmare. But I do love the concept and I think that just like LLM agents were a new layer on top of LLMs, Claws are now a new layer on top of LLM agents, taking the orchestration, scheduling, context, tool calls and a kind of persistence to a next level. Looking around, and given that the high level idea is clear, there are a lot of smaller Claws starting to pop out. For example, on a quick skim NanoClaw looks really interesting in that the core engine is ~4000 lines of code (fits into both my head and that of AI agents, so it feels manageable, auditable, flexible, etc.) and runs everything in containers by default. I also love their approach to configurability - it's not done via config files it's done via skills! For example, /add-telegram instructs your AI agent how to modify the actual code to integrate Telegram. I haven't come across this yet and it slightly blew my mind earlier today as a new, AI-enabled approach to preventing config mess and if-then-else monsters. Basically - the implied new meta is to write the most maximally forkable repo and then have skills that fork it into any desired more exotic configuration. Very cool. Anyway there are many others - e.g. nanobot, zeroclaw, ironclaw, picoclaw (lol @ prefixes). There are also cloud-hosted alternatives but tbh I don't love these because it feels much harder to tinker with. In particular, local setup allows easy connection to home automation gadgets on the local network. And I don't know, there is something aesthetically pleasing about there being a physical device 'possessed' by a little ghost of a personal digital house elf. Not 100% sure what my setup ends up looking like just yet but Claws are an awesome, exciting new layer of the AI stack.

@karpathy The outcome is modest (basically this could have been an excel spreadsheet), but the building is more fun and the potential is Great. Skill store will replace app store if AI replaces the OS.

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.

@Blznbreeze @karpathy I have the same yearly checklist -- in Google Keep.

@karpathy My wife got mad at me for neglecting my home maintenance duty so I vibe coded and android app that reminds me of my seasonal home maintenance.

@dcolascione That's really ridiculous. Thanks for the info. Now I know I want to avoid laptops and keyboards with this key in my next purchase. In Windows, I'd have used AHK to remap. But exactly this MS behavior already drove me away from Windows.

MUST WATCH. This NAILS the difference between 90's kids who played video games and Gen Z kids. Thanks to @ShortN40 for the tip on this.

@karpathy I listen to my RSS feed during car commute. Works best for me.

Finding myself going back to RSS/Atom feeds a lot more recently. There's a lot more higher quality longform and a lot less slop intended to provoke. Any product that happens to look a bit different today but that has fundamentally the same incentive structures will eventually converge to the same black hole at the center of gravity well. We should bring back RSS - it's open, pervasive, hackable. Download a client, e.g. NetNewsWire (or vibe code one) Cold start: example of getting off the ground, here is a list of 92 RSS feeds of blogs that were most popular on HN in 2025: gist.github.com/emschwartz/e6d… Works great and you will lose a lot fewer brain cells. I don't know, something has to change.

@gothburz Absolutely agree. After recent phone reset, the only app that I can't log back into, is Microsoft Authenticator. Stuck in the login loop asking to confirm by Authenticator 🤦 Luckily I don't depend on Microsoft for anything important 😅

Microsoft asked me to sign in. I signed in. Microsoft signed me out. It recommended I close all browser windows. I was trying to check my email. Now I'm closing browser windows. That's the user experience. The login took 4 clicks. The logout took 0. For threat actors it's also 0 click but that's off topic. I didn't ask to log out. I wanted to sign in. Microsoft decided for me. Microsoft knows what's best for their user base. Just like when they put Copilot in everything. Nobody asked. Everyone received. That's empowerment. That's empowerment. Somewhere in Redmond, a PM got promoted for this flow. "Streamlined authentication experience." "Reduced session persistence friction." "Proactive security posture." I just wanted to see if my mom emailed me. $3 trillion market cap. $37.5 billion on AI infrastructure. Can't keep me logged into Outlook. That's priority alignment. "It's a good idea to close all browser windows." It's a good idea to check my email. We have different ideas. Microsoft and me. I'll try again. Four more clicks. Another sign-in. Another sign-out. That's synergy.

@0xEthan Just don't miss the next chance, y'all

In 2011 you could visit this website and claim 5 Bitcoin for free

Post a picture YOU took. Just a pic. No description.

@earthcurated @CrispeThe

Post a picture YOU took. Just a pic. No description.

@mindcriticalthe @f_wintersberger @AngelLamuno AI is just a tool. Can you have a "Excel strategy"?

@f_wintersberger @AngelLamuno Should the EU have no AI strategy, really?

I listen to this, and after 30 seconds, I am confident to say that the ship has sailed. Europe will play absolutely no role in the AI race.

@itsalexvacca @threadreaderapp unroll

BREAKING: MIT just completed the first brain scan study of ChatGPT users & the results are terrifying. Turns out, AI isn't making us more productive. It's making us cognitively bankrupt. Here's what 4 months of data revealed: (hint: we've been measuring productivity all wrong)

@lobacake It's madness 😂

@CNviolations At least it was worth for the onion 😂

Bad decisions were made.