Firehose

AI models have demonstrated the ability to reimplement entire software programs from scratch, with some models successfully completing tasks that would take human engineers months to solve. The MirrorCode benchmark, co-developed with METR, tests AI models on long-horizon coding tasks by requiring them to reimplement 25 target programs, including Unix utilities, data serialization tools, and bioinformatics software, without access to the original source code. AI summary

Boris Cherny, head of Claude Code, experimented with directing Claude to rewrite the Claude desktop app from Electron to Swift, but the task is still running after 14 days, suggesting it's unlikely to succeed in rewriting the app's design and functionality. The actual problem with the current app is its poorly designed UI, not just the technical details of using Electron. Porting the app to Swift won't solve the design issues, and the current design is un-Mac-like. AI summary

Sprocket is an AI agent that can work on both hardware and software development, retrieving context from the web, buying parts, creating schematics, and generating assembly instructions. It can be run through a desktop app, browser, or CLI, with options for customization and deployment. Sprocket uses a Convex deployment for its runtime. AI summary