
Kai INUI
23.6K posts

Kai INUI
@_kaiinui
Rikka CEO. Running a small game studio / Poker, LoL / とっても小さなゲームスタジオをやってます ← DMMへM&A ← ピックアップ社共同創業



Subagents are now available in Codex. You can accelerate your workflow by spinning up specialized agents to: • Keep your main context window clean • Tackle different parts of a task in parallel • Steer individual agents as work unfolds



About 30% of GPT-5.4 traffic in Codex is going out in /fast mode. It looks like frontier intelligence at 1.5X speed and 2X the price has PMF. What is the highest speed / price ratio that you would be willing to pay for?


The government is asking for public comments on whether banks should be able to deny you from buying legal goods at their own whim (i.e. how they're cracking down on art, subscribestar, itchio) TELL THEM you don't want to be told how to spend your money federalreserve.gov/apps/proposals…

Introducing Void, the Vite-native deployment platform: 🚀 Full-stack SDK ⚙️ Auto-provisioned infra (db, kv, storage, AI, crons, queues...) 🔒 End-to-end type safety 🧩 React/Vue/Svelte/Solid + Vite meta-frameworks 🌐 SSR, SSG, ISR, islands + Markdown 🤖 AI-native tooling ☁️ One-command deploys void.cloud

openai should just replace chatgpt with codex

OK, well. I ran /autoresearch on the the liquid codebase. 53% faster combined parse+render time, 61% fewer object allocations. This is probably somewhat overfit, but there are absolutely amazing ideas in this.


unreasonably excited about this tool we're building to allow agents to "see" the visual work they're doing. time to kick storybook to the curb any wishlist ideas I should add? folio.stage.obvious.ai/obvious/reacts…






