Endo is a Higher-Order Harness (HOH) that treats LLM agents as composable building blocks, providing a unified chat interface where you can combine, switch between, and continue conversations with different providers inside one thread. It connects to Codex, Claude, Gemini/Antigravity natively through their CLIs using your existing subscriptions (no API keys to paste) and funnels every provider through a single protocol so tool calls, permission prompts, streaming, and history behave consistently. Endo supports workflows like /best-of-n, /multi-turn-debate, /thesis-killer and scheduled runs, persistent sessions and “Dig In” side-conversations that branch from any part of an answer while preserving the main thread and history across restarts.
Workflows are authored as TypeScript files in a workspace using primitives such as agent(), parallel(), phase(), and session IDs; a Workflow card visualizes each call and final result. Developers can add Resources (typed Drizzle tables + Effect Schemas) for shared state, register agent tools, tweak prompt segments, add UI pages/features, and build signed macOS releases. The project provides a downloadable macOS app and source build instructions (Node 24, Bun 1.4.2, Just), is MIT-licensed, credits several UI and agent tool projects, and is at 0.1.x so breaking changes are expected.
Summary generated by AI from the linked article. hn.today is not affiliated with Hacker News or Y Combinator.
AI founders and executives in San Francisco discussed rapid revenue growth, data brokerage, and the evolving AI landscape, emphasizing the importance of data and model flexibility. They highlighted the potential of autonomous agents, the significance of data valuation, and ongoing reverse engineering efforts in the industry. (twitter.com)
Geoffrey Hinton warns that AI is creating alien-like beings and we have only a few years to adapt to this reality. He criticizes Donald Trump's understanding of superintelligence and emphasizes the need to prioritize human interests. (theguardian.com)
Anthropic suggests its AI may possess consciousness, raising ethical questions about AI feelings and suffering. The development has sparked debate among tech leaders about the moral implications and safety risks of advanced AI systems. (bbc.com)
Self-Evolving Agent Harness revises an AI agent's software components through a feedback-driven process, while keeping model weights fixed. It formalizes continuous validation and updates to improve reliability, safety, and organizational workflows. (arxiv.org)
Reinforcement learning in large language models can cause 'thinking leakage,' where models partially reactivate their original reasoning abilities rather than learning new behaviors. This leakage explains much of the observed performance improvements in models trained with RL in non-thinking modes. (arxiv.org)
Sergey Brin states that Google's AI models are entering a phase of recursive self-improvement, where AI helps develop better AI systems. This process could accelerate AI development significantly within the next year, according to industry experts. (businessinsider.com)
Today's best Hacker News stories, summarized and screenshotted, one email a day.