ryanwaits

feel like i’m at that point in monopoly when I have like $50 left after buying everything i landed on and really need people to land on my sh**

someone is cooking

Karpathy is telling you something most product teams haven’t internalized yet. The new distribution channel for software is agents. Agents don’t browse your marketing site, watch your demo video, or click through your onboarding flow. They call your CLI. They hit your MCP server. They read your docs programmatically. If none of those surface areas exist, your product is invisible to them. Look at how fast this moved. MCP went from zero to 97 million monthly SDK downloads in twelve months. 10,000+ active servers. OpenAI, Google DeepMind, Microsoft, and Cloudflare all adopted it. By December 2025, Anthropic donated MCP to the Linux Foundation because the standard had already won. Running an MCP server is now compared to running a web server. That’s the new baseline for product discovery. 85% of enterprises are expected to have AI agents deployed. Those agents need structured, programmatic access to your product. They need CLIs, MCP endpoints, and machine-readable documentation. A beautiful React dashboard is worthless to an agent trying to pull data into a workflow at 3am. This tells you everything about why Karpathy’s framing of CLIs as “legacy” technology is so precise. Legacy means battle-tested, standardized, universally parseable. stdin/stdout, flags, JSON output. The entire Unix philosophy was accidentally designed for AI agents decades before they existed. Your competitor ships an MCP server and suddenly every Claude Code user, every Cursor session, every autonomous workflow can discover and use their product. No human ever visits the website. No sales call. No onboarding email. The agent just finds the tool and starts using it. The companies that win the next 24 months are the ones building agent-accessible surface area right now. The ones that lose are still optimizing their landing page above the fold.

@LuvKaizenAgency @gauntletai you pass an auth handler that runs during the ws upgrade, so you can validate however you like (jwt, session, api key) presence is in memory per room heartbeats, auto idle detection and cursor tracking broadcast in realtime

@ryan_waits @gauntletai Stop throwing money at KOLs, how’d you handle auth + presence?

earlier this week, we were tasked with building a collaborative whiteboard for our first @gauntletai project. so naturally, i went a step further and decided to build a liveblocks alternative. introducing Lively lively.waits.dev 10 packages. crdt sync engine. 40+ hooks. multiplayer websockets. cli + ui components. check out the 6+ examples, including a notion clone, ide, and realtime workflows.

@nickscamara_ @ctatedev @firecrawl i don’t know what i’m looking at but it’s beautiful

the perfect web automation stack -> Claude Sonnet 4.6 -> Agent browser (@ctatedev) -> Running on @firecrawl browser sandbox npx skills add firecrawl/cli

@delba_oliveira 🔥

👩‍🔬 Code diffs!

Everything we're doing to make codebases "agent-ready" (better docs, less dead code, smaller surfaces) engineers always needed too. Agents just have zero tolerance for the entropy humans learned to work around. They can't "just know" a file is outdated or a code path is dead. They take your codebase at face value, which means it finally has to be worth taking at face value.

when a developer ships in a day what used to take a month, the bottleneck moves. it’s not code anymore, it’s product sense, customer understanding, taste. the grunt work compresses. the human judgment work expands. that’s not fewer jogs. that’s different ones.

a developer using ai to write code isnt being replaced by ai. they’re using a tool. that’s what tools are for. if a machine can do a job better than you can, the right response isn’t fear, it’s relief. you’d rather use a bulldozer than a shovel. automation doesn’t eliminate work. it changes the nature of it.

ai is legitimately wild. i use it daily. this isn’t a “nothing to see here” take. but the leap from “this is powerful” to “your job is disappearing” skips over the most important part. what people actually do when things change. people aren’t static. neither are markets.

@every @kieranklaassen @danshipper wonder how much of the “single dev = five devs” gain is just skipping team dynamics aligning on vision, interpreting ideas differently, committee design coordination tax might be the real bottleneck, not planning or coding

A single developer can now do the work of five. @kieranklaassen and @danshipper share the compound engineering framework that makes this possible at Every—and they've open-sourced the exact workflow. every.to/source-code/co…

“we are all loops”

Build something you want.

xscore import ~/Downloads/archive imports and embeds. xscore "your draft" scores against your hits, and tries to predict engagement.

built a cli to score posts using this. download your X archive, import to sqlite, embed with openai. scores drafts against your own engagement history using algo weights, lets see how well it works lol

@haydenbleasel @vercel yall need to chill 🔥

▲ @Vercel AI Elements, Code Edition This is the single BIGGEST component drop we've ever done. A brand new set of components designed to help you build the next generation of IDEs, coding apps and background agents. Let's see what's new! 👇

@ryancarson nice. my feed feels like everyone arriving at similar ideas, independently, all at the same time

I’ve figured out a new way of working that’s unlocked my speed of iteration massively. Here’s how it works: I have a simple cron job that runs every night at midnight. It gathers information from my database on user activity, marketing stats, and a couple other data points that are important. It then feeds that data into Opus 4.5 and asks for one important action item that I should take based on this data, and then emails me. It also creates a markdown file with the recommendation, which is then stored in my reports folder in the GitHub repo. (This means I can fire up Amp anytime and chat either all of the historical recommendations whenever I want - learning about patterns.) I then look at this email every morning and decide whether or not to take action on it. Almost every time it surfaces something really valuable for me to iterate. So I just open Amp, tell it to action idea, and then ship it. Obviously, the next iteration of this is just to have Amp autonomously implement the suggestion by itself, and then I'll wake up to a PR instead of an email. Right now, though, I like the Human-In-The-Loop version of this. And as soon as we iterate enough like that, I'll probably just set it up to automatically take the suggestion, create the PR, and then I'll have a look at it. Obviously, you can take this loop even further by having many parts of your business evaluated this way. What's interesting to me is that this is what I used to rely on my VP of Marketing, my VP of Engineering, or my VP of Sales to do, but it happens automatically for about $0.15 per day.

“bro I spent all weekend in Claude Code it’s incredible” “oh nice, what did you build?” “dude my setup is crazy. i’ve got all the vercel skills, plus custom hooks for every project” “sick, what are you building?” “my setup is so optimized, i’m using like 5 instances at once”

@claudeai really prefers api sdk over agent sdk, you gotta press it hard