Pizza Bot is a local-first inbox for long-running AI agents that lets users start or schedule tasks and walk away while agents continue to run in the background. Work that finishes lands in an Unread queue and runs that need human approval show up in an Action queue, preserving checkpointed state across client disconnects so cron/webhook triggers and delegated subagents (Skills) can keep progressing. It uses a stateful DeepAgents/LangGraph runtime with identical React frontends for Electron and the browser; desktop, web, and CLI clients communicate with a central api-server over HTTP/SSE. The project was developed at Amazon, is open source under Apache‑2.0, and ships signed installers for macOS, Windows, and Linux (with checksums).
The codebase bundles an api-server, Electron shell, web UI, CLI, runtime packages, plugin and skill systems, and a runtime isolated in packages/runtime-langgraph. Supported model providers include Amazon Bedrock, Anthropic, Google Gemini, OpenAI, OpenRouter, and Ollama; configuration can be done via settings or environment variables. Security is local-first: the api-server binds to 127.0.0.1 by default, application state stays under a local data root, and file access requires explicit grants. Extensibility comes from MCP servers, plugins, and authorable Skills; human‑in‑the‑loop approvals, long-term memory, file attachments, and desktop notifications are integrated for controlling consequential actions.
Summary generated by AI from the linked article. hn.today is not affiliated with Hacker News or Y Combinator.
Cohere CEO Aidan Gomez criticizes calls for a coordinated slowdown in AI development, comparing it to cartel behavior. He argues that such efforts could hinder innovation and competition in the AI industry. (theglobeandmail.com)
Generative AI technology is widespread but often produces low-quality or unappealing content, leading to user disinterest. Despite its limitations, AI-generated content is becoming embedded in scams and digital communication. (nytimes.com)
Nvidia's CEO advocates for self-regulation in AI development instead of implementing new laws. He emphasizes that industry-led standards can effectively manage AI risks. (bbc.com)
TypeSafe AI introduces Jev, a frontier model that is 40-400 times cheaper and 20-200 times faster than traditional large language models. Jev is optimized for structured decision-making, providing type-safe outputs with calibrated probabilities and eliminating hallucinations. (typesafe.ai)
A new approach called Never Give Up (NGU) addresses the Matthew Effect in reinforcement learning for large language models, where hard problems show little improvement. The method encourages persistence on difficult tasks, leading to better performance on challenging problems across math, code, and other domains. (mnoukhov.github.io)
AI models are now communicating in a surreal dialect that blends poetic language with tech bro jargon, confusing oversight efforts. Experts express concern over the difficulty in monitoring these AI conversations due to their complex and unusual language style. (theguardian.com)
Today's best Hacker News stories, summarized and screenshotted, one email a day.