⚡️ ri97 ⚡️

CYBERTRUCK X NYC

POV : USING CLAUDE OPUS 4.7 TO JUST RENAME A VARIABLE

We’re introducing a new GitHub Certified: Agentic AI Developer (GH-600). As AI agents become part of modern development workflows, this role-based certification focuses on how developers and teams operate, supervise, and integrate agents across the SDLC. If you’re already working with tools like GitHub Copilot or exploring agent-driven workflows, we’d love your input. Learn more and get involved. msft.it/6013vRHHZ

you know the startup is gonna be insane when the founding engineers look like this

The human-perceived RGB is image 1 and the Tesla AI photon count reconstruction is image 2. This is why Tesla FSD can see so well at night or through extreme glare.

@ananayarora Same feeling as precovid WWDC

Anthropic getting ready for its first ever developer conference on May 6 in SF

Most AI companies are racing to ship product. Few are thinking about what it takes to actually sell to enterprises. Michael Grinich (@grinich) is the founder and CEO of WorkOS, the enterprise authentication and identity infrastructure layer used by Anthropic, OpenAI, Cursor, xAI, and hundreds of other fast-moving companies. Before WorkOS, Michael was a founder at Nihilus, where a painful first experience with enterprise sales planted the seed for what would eventually become WorkOS. What we discussed: (00:00) The SaaS apocalypse thesis — and why Michael thinks it's wrong (01:09) Introducing Michael Grinich — MIT, Dropbox, and the road to WorkOS (05:14) The Stripe origin story and early MIT startup network (07:03) Drew Houston, Dropbox, and what convinced Michael to build (09:05) Founding Nihilus: three maxed credit cards and two days from missing rent (11:00) How to generate startup ideas: volume over quality, the notebook habit (14:05) Finding sticky ideas — the ones you keep coming back to (17:10) Why the energy behind an idea matters as much as the idea itself (20:16) What experience gives you: pattern recognition and a framework for new scenarios (24:05) The moment Michael saw the enterprise auth problem and knew it was real (27:02) How Anthropic, OpenAI, and Cursor ended up as WorkOS customers (31:16) Why WorkOS sits at the security and growth layer for AI companies (35:06) The ultimate boss battle: building developer tools for other developers (39:06) Why developer customers give the best product feedback — and why that's a gift (44:04) The SaaS apocalypse revisited — and what's actually happening to software (47:17) How AI compressed the timeline to enterprise-ready from months to a day (53:03) Tying company value to something durable through technology waves

See the announcement today from @brian_armstrong at Coinbase in the attached pic. Managing fleets of agents effectively is the most high-impact thing you can do now for your company and for yourself personally. I have the most advanced set of open-source, provider-agnostic agent tooling to do all that at scale: MCP Agent Mail for inter-agent messaging and file reservations (avoid the git worktree anti-pattern and merge hell). beads_rust for agent-intuitive task management that works well across all harnesses. bv for triaging tasks based on the graph structure of task dependencies (maximize development velocity through de-bottlenecking). ntm for doing agent orchestration (creating and managing swarms of Claude Code and Codex instances). dcg for preventing the agents from doing destructive things. cass for letting agents instantly search all session history globally for any agent harness ubs for polyglot “super linting” and bug finding. You can find all of these on my GitHub: github.com/Dicklesworthst… Or install all of them automatically on a Linux cloud server using the acfs setup wizard, available for free at agent-flywheel.com And see my complete guide explaining how to do planning with these tools, which is the key to achieving high code quality: agent-flywheel.com/complete-guide And then to make these tools as effective as possible, I have a complete suite of powerful and sophisticated agent skills that are deeply integrated with the tooling available at jeffreys-skills.md The skills are $20/month. You don’t need to use them but they’re absolutely worth it if you want to get the most out of the tools and the agents in general. Why do this now? What’s happening at Coinbase is going to happen soon at every well-managed technology company within the next year. The writing is on the wall. This isn’t alarmist fear mongering. This is the inexorable reasoning of the market and capitalism grappling with these irresistible economic forces. Don’t wait and become a statistic, facing a structurally difficult job market without the skills that all well-positioned employers are going to be looking for. Take action NOW to master these technologies and empower yourself.

BB Urich killed it with this one

$999 audits are BY FAR the best way to start an AI business. Here's the playbook: 1. Day 1: Text 20 people in your warm network. Friends, family, ex-coworkers, gym, church. 2. Week 1 to 2: Run free 20-min audits. Walk through their workflow. Show what AI can automate. 3. Week 2 to 4: Land your first 3 paying clients. They came directly from those free audits. 4. Week 4 to 6: Bank the referrals. One free client refers two more. Word of mouth kicks in. 5. Week 6+: Charge $999 for a 45-minute audit. Case studies stack. Pricing power follows. 4 audits a month at $999 = $48,000 a year from 2-hour afternoons. Then upsell the implementation.

Purpose-built for autonomy Cybercab in production now at Giga Texas

shadcn/ui is now available as a Cursor plugin. Thanks @ericzakariasson. Run: /add-plugin shadcn

try the shadcn plugin in cursor!

I want to thank everyone for the outpouring of love and thank you for believing in me to lead the company that has always put you at the center of our work. This is not goodbye. It’s a hello to John and I can’t wait for you to get to know him like I do! 🙏

Robert Downey Jr.’s accent as Doctor Doom reportedly sounds something like this 😱🤯

Writing and acting so good it made me feel kinda bad for Fisk.

A single 𝗖𝗟𝗔𝗨𝗗𝗘.𝗺𝗱 file just hit 15K GitHub stars. (derived from Karpathy's coding rules) Andrej Karpathy observed that LLMs make the same predictable mistakes when writing code: over-engineering, ignoring existing patterns, and adding dependencies you never asked for. If you've used AI coding assistants, you've hit all of these. But here's the thing: If the mistakes are predictable, you can prevent them with the right instructions. That's exactly what this 𝗖𝗟𝗔𝗨𝗗𝗘.𝗺𝗱 does. You drop one markdown file into your repo, and it gives Claude Code a structured set of behavioral guidelines for your entire project. This is a big deal. - Built entirely around prompt engineering for AI coding assistants - No framework, no complex tooling, just one .md file that shapes behavior Developers are moving past "use AI to write code" and into "engineer the AI's behavior so the code is actually good." The Claude Code ecosystem is growing fast, and the best tools in it aren't always software. Sometimes they're just well-crafted instructions. 100% open-source. I've shared a link to the GitHub repo in the next tweet!

“Can I get the WiFi password?” “Yeah it’s on the router” The router: