claude code is having it's cursor moment after karpathy sensei's post. never been a better time to try it. my latest blog on how to get the most out of claude code 2.0 and other agents in general is up now. grab a chai and have fun reading! sankalp.bearblog.dev/my-experience-…

As a New Year's present, I've just finished a little prettier plugin that wraps all Tailwind classes with shadcn 's `cn()` function (and handles the function import). I got tired of having to request it every Peer Review... npmjs.com/package/pretti…

Life in 2026

There’s a sentiment that AI is moving so fast we have to keep up or get left behind. And I get it. But also the changes aren’t that difficult to comprehend, if anything it’s just getting easier. I think a strong case can be made to take a couple of days every 3- 6 months to

I'm Boris and I created Claude Code. Lots of people have asked how I use Claude Code, so I wanted to show off my setup a bit. My setup might be surprisingly vanilla! Claude Code works great out of the box, so I personally don't customize it much. There is no one correct way to

Such a great breakdown of how to use Ralphy and how it all works

Straight cookin’

/lfg I really like to create slash command that call other slash commands for nice composable flows.

Anyone else getting a ton of “this is the shift”, <some form of agreement > …And <this> actually makes it <x> not <y> From ChatGPT at the moment? It’s super annoying…

Here are my CLAUDE​.md additions for making plan mode 10x better Before: unreadably long plans After: concise, useful plans with followup questions aihero.dev/my-agents-md-f…

Today, Node.js published a security release for Node.js that fixes a critical bug affecting virtually every production Node.js app. If you use React Server Components, Next.js, or ANY APM tool (Datadog, New Relic, OpenTelemetry), your app could be vulnerable to DoS attacks. 👇

I love that phrase so much! “Uncommon care” 🥰🥰🥰

It's so over

x.com/i/article/2021…

100% of code written by agents. 100% reviewed by agents. Humans show up at the end. Ryan Carson and leading startups are already doing this. He broke down the full setup on the pod. The hard part? The plumbing. i.e. Terraforming your repo so the agent can see everything,

x.com/i/article/2032…

Everyone who's worked with AI a lot agrees: LLM's hallucinate. A LOT. But to this day, I see friends and family trusting ChatGPT blindly, whether it's is working off retrieved data or not. So, I made this. Share it with anyone who you think trusts AI too much.

I wanted to share a bunch of my favorite hidden and under-utilized features in Claude Code. I'll focus on the ones I use the most. Here goes.

list of my favourite inspo sites: → land-book.com → inspo.page → saaspo.com → mobbin.design → rebrand.gallery made it a habit to look at designs everyday and see what's new. even 15+ minutes before the work starts is

Memory makes your agent smarter over time. The agent harness is key to the memory layer. You can't bolt one onto the other after the fact. Every decision the harness makes - what goes in context, what survives compaction, how skills get surfaced, how the working directory is