Chuck C

What creates value and doesn't feel like work to you ? Do that.

@kr0der Broke mcps for me though 🥹

i feel like no one's talking about the new Cursor plugin marketplace enough, this feels like one of the most useful releases recently in my opinion

@thepaulbalaji Im using greptile atm and it’s rly good, but thinking about adding others to catch more bugs early. Whats your take on this, is it really worth or is it just marginally better ?

Avengers: Assemble

@AgrawalHridaya @thepaulbalaji is graphite rly good for reviews ?

@thepaulbalaji how we leaving out greptile, copilot, graphite 🥀

who’s gonna be the Kanye of software?

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 The idea of an "app store" of a long tail of discrete set of apps you choose from feels somehow wrong and outdated when LLM agents can improvise the app on the spot and just for you. 2) Second, the industry has to reconfigure into a set of services of sensors and actuators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.

Anything you can do in Obsidian you can do from the command line. Obsidian CLI is now available in 1.12 (early access).

A prototype is worth a thousand meetings. Prototypes are so easy to make now, there’s zero reason not to do it. Started to quickly vibe coding prototypes for every new major features to align business, design and dev and it makes everything SO much faster.

@thepanta82 @theo Was thinking the same lol

@theo Someone's been watching a lex friedman podcast

Imagine that, a few years ago, you got tired of build steps and checks in your codebase, so you remove TypeScript. That one (seemingly) small decision just made it so no AI agent can reliably contribute code in that codebase. Great work. I bet you feel smart now.

@sgrove Amazing talk. Randomly stumbled on it; had to find u here after watching.

I've been on a kick about clear thinking and communication recently. It's critical for developing safe, useful models, and applications built on top of them.

@witsdev @vercel damn, well done

here's how we designed "Find," the new universal search in the @vercel dashboard

@desmondhth wow

Build in public was my focus in 2024. But start of 2025, I realized that it has been a bottleneck for me to go to the next level. I need to think bigger. So I took a 180 days break from X. In the last 180 days, Rise made $1M. I'll be back on X next week. Stay tuned gang✌️

@GiovanniIncasa irl It’s weird

@chuckbuildsit Where have u been sir?

hi i'm back, who's still here ?

@ItsMeBenChan Damn yes !!

@chuckbuildsit hi

@RayFernando1337 @jimclydego @cursor_ai Perfect I just reached it 😂

@jimclydego @cursor_ai It’s going away

HOLY GUACAMOLE! Unlimited Cursor usage for $20/month (with rate limits). This is an incredible deal for access to all ai coding models with max context windows. If you are LOCKED IN grab the $200/month Ultra plan for 20x usage + PR indexing & Priority Access to new features.

@joshmanders Why ?

Stop responding with Adonis. It's not even close.

I wish JavaScript had an actually capable backend framework along the lines of Rails, Laravel, Django and Phoenix. I started down the path of building one but it's a monumental task and every time I discussed it with someone who does JS they were always confused at why anyone would use a full stack framework in JavaScript when you can just npm install 303 random packages that haven't been updated in years and write 10k lines of boilerplate, or they get confused at why one would need all that ability.

@elysian_labs @manic_pixie_agi Aaaah, my bad, it’s loosing conversation history, not memory

@elysian_labs @manic_pixie_agi Huh but why is there a warning about loosing memory when starting a new conversation?

@elysian_labs Related: Seren mentions setting up reminder then I need to fight to get the reminders 😂 then when i realize it forgot a reminder I need to fight again to prove my point before it finally admits it. Idk if it’s a feature of a bug but, fun times

@thekitze damn @thekitze

💀