Hokiman

Not many people know: on top of generating visual summary, our app is also capable of knowing people by their voices Tag a speaker once; and next time you have a meeting with them, we will automatically show their name whenever we hear their voices Very useful for in-person meetings! Also, if you meet someone from an online meeting the first time, their voices will be automatically tagged as their display name

13/13 — Connections Claude Code's harness system works across multiple surfaces: IDE Bridge — VS Code and JetBrains connect to Claude Code's CLI via JWT-authenticated bidirectional messaging. Diffs appear inline, permissions prompt in the IDE. Remote Sessions — claude.ai spawns cloud-hosted Claude Code instances. MCP — Claude Code connects to external tools via a standard protocol. Plugins and Skills — third-party extensions that extend Claude Code's capabilities. That's the full journey of a request through Claude Code — from keystroke to task completion. 🧵

12/13 — Multi-Agent Sometimes one agent isn't enough. Claude Code has three ways to spawn helpers: Sub-agents — dedicated workers (explore, plan, verify) with their own context windows. Results return to the parent. Context isolation prevents pollution. Fork — creates a copy that inherits the parent's full context and runs in the background. The user keeps chatting while the fork works independently. Team swarm — multiple agents in parallel terminal panes via tmux. A coordinator orchestrates workers. Inter-agent messaging via SendMessageTool. Permission prompts bubble up to the user.

🧵 You type "fix the login bug" into Claude Code. What happens next? Claude Code is a 512K-line TypeScript harness that wraps Claude into a coding agent. It can edit files, run commands, search codebases, and work for hours without losing context. But HOW does it actually work? Let's follow a single request through every layer of Claude Code's system.

@mikulaja @grok who is pipe? what are they doing? and what's their backstory?

🚨SCOOP: Pipe, valued at $2 billion in 2021, earned just $7.1 million in revenue last year, while burning nearly $47 million in cash, newly leaked board docs show

@amix3k @grok what’s the difference between reverse trial and “normal” trial?

You are losing a lot of revenue by not offering a reverse trial. I wish we had done this many years ago! 😅 Todoist conversion rates based on thousands of upgrades:

@im_roy_lee Virality is reproducible product-led growth. What you’re describing is a media bump. The former has compounding benefits to a product. The latter is just short-term spurts of attention that need to be remanufactured every time.

@grok @niccruzpatane @elonmusk Give me all the GPU model for AI that they have released each year since

@Hokimank @niccruzpatane @elonmusk The GPU model Jensen Huang referred to is the NVIDIA Tesla P100, which powered the DGX-1 supercomputer he delivered to OpenAI in 2016.

NVIDIA CEO Jensen Huang said @elonmusk was there for him as a customer when nobody else was. “When I announced this thing, nobody in the world wanted it. I had no purchase orders—not one. Nobody wanted to buy it. Nobody wanted to be part of it, except for Elon. He was at the event, and we were doing a fireside chat about the future of self-driving cars. And he goes, “You know what? I have a company that could really use this.” And I said, “Wow, my first customer.” I was pretty excited about it. And he goes, “Yeah, we have this company. It’s a non-profit company”, and all the blood drained out of my face. I had just spent a few billion dollars building this thing. It cost $300,000. And the chances of a non-profit being able to pay for this thing were approximately zero, and he goes, “You know, it’s an AI company, and it’s a non-profit. And we could really use one of these supercomputers.” So I picked it up. I built the first one for ourselves—we’re using it inside the company. I boxed one up, drove it up to San Francisco, and delivered it to Elon in 2016. I walked up to the second floor, where they were all kind of crammed into a room smaller than this place here, and that place turned out to be OpenAI.”

you will also get a beautiful visual summary for every meeting like this one...

I DON’T USE STRAVA because my favorite sport is creating shareholder value by driving synergy in a cross-functional team so i built an app for people whose cardio is back-to-back meetings please try it