Developer Daniel Hayes Smith built ClearTime, a visual timer designed to help with ADHD-related time blindness after a health scare led him to stop stimulant medication. ClearTime uses a solid disc of color that shrinks as time passes so users can glance and feel how much time remains; the same dial and brand mark appear across Mac (floating timer/menu bar), iPhone (widgets, Live Activities, Dynamic Island), Apple Watch (complication/glance), and Apple TV (shared room timer). From first commit to functioning TestFlight builds on all four platforms took about five hours, with roughly 45 minutes of hands-on coding; the apps are native Swift/SwiftUI targets, not wrapped web apps.
The build was driven by a deliberate multi-agent AI workflow: ChatGPT for product definition and constraints, Claude Design for logo, dial geometry-as-code, color tokens, platform reference boards, accessibility, and a build guide that resolved conflicts, and Claude Code (Claude Opus 5.5) to implement the codebase. The team abandoned an initial Tauri/Expo plan in favor of a single Xcode workspace with seven targets and a shared package for the timer engine, used Xcode’s MCP bridge so the agent could edit the project, and gave the coding agent explicit rules to solve routine decisions. TestFlight provided the final verification, and the process produced design assets, a showreel, and receipts documenting the workflow.
Summary generated by AI from the linked article. hn.today is not affiliated with Hacker News or Y Combinator.
OpenAI and Synopsys have announced GPT-Synopsys, a frontier intelligence platform designed to revolutionize chip design. The collaboration aims to enhance AI-driven automation and optimization in semiconductor development. (news.synopsys.com)
The US government's new AI chatbot has refrained from debunking claims made by Trump. The chatbot is currently experiencing connection issues that prevent full functionality. (techxplore.com)
OpenAI reduced the usage allowance for the $200 plan from 20x to 10x the ChatGPT Plus limit starting October 30, 2026. A new Pro 500 tier offers 25x the usage of Plus for users needing more capacity. (news.ycombinator.com)
Vectorless, reasoning-based retrieval-augmented generation (RAG) is introduced by VectifyAI to improve AI reasoning without relying on vector embeddings. The approach enhances reasoning capabilities in AI models, as detailed in their GitHub repository. (github.com)
The video features interviews with AI CEOs in 2026 discussing the future of artificial intelligence and its impact on industries. It highlights advancements in AI leadership and technological integration. (youtube.com)
A GitHub project involving 'torturing' large language models has sparked a heated debate about AI consciousness and model welfare. Experts agree that LLMs are not sentient, but some AI safety advocates worry about their 'mental health' as models become more advanced. (404media.co)
Today's best Hacker News stories, summarized and screenshotted, one email a day.