Octomind is an open-source, Rust-based runtime for AI coding agents, designed to work beyond an interactive chat window. A single binary can run a model-powered agent in a terminal, accept piped input for scripts and CI, operate as a background daemon, serve integrations over WebSocket, or act as a sub-agent through ACP. Agents can inspect and edit repository files, run shell commands, search code, and delegate work using MCP tools. Configuration for models, roles, tools, budgets, and safety rules is kept in TOML; users can choose hosted or self-managed model providers and set spending limits. Packaged “specialists” bundle prompts, models, MCP servers, and permissions, while adaptive context compression is intended to keep long-running tasks efficient.
A central design claim is that autonomous coding needs deterministic controls rather than approval prompts that assume a person is watching. Octomind’s guardrails can block tool calls before execution, run hooks after results to feed errors back to the agent, and use validators after turns. Its README also reports a benchmark on 25 held-out bug-fix tasks drawn from merged pull requests across five programming languages: Octomind with GLM-5.2 solved 24, versus 23 for Claude Code with Claude Opus 5, 21 for Codex with GPT-5.6-sol, and 19 for OpenCode using the same GLM model. Reported Octomind cost was $63.43 and wall time 3.6 hours; the results are presented as comparisons of complete agent setups, not isolated model performance.
Summary generated by AI from the linked article. hn.today is not affiliated with Hacker News or Y Combinator.
Tianhua Chen’s 195-page primer derives the mathematical foundations behind major generative AI models, including VAEs, diffusion models, GANs, and normalising flows. It connects these approaches in an accessible, visually enhanced guide for students, researchers, and practitioners. (arxiv.org)
U.S. tech giants’ hidden debt tied to AI investment rose 90% in six months, reaching $3.2 trillion. The surge highlights the scale of financing behind the AI infrastructure buildout. (asia.nikkei.com)
Revolut replaced Claude Code and Codex as its engineers’ default coding tools with a self-hosted Chinese GLM model, reporting a 90% lower AI bill and faster development. The company says results rely on extensive tuning and exclude some costs, while frontier models remain available for demanding tasks. (dealroom.co)
Google plans to cut off Search access to schools that ban generative AI. The policy links access to its search engine with schools’ rules on generative AI use. (forbes.com)
Itch.io says game-page uploads doubled to more than 6,000 a day, driven mainly by first-time creators using AI tools, without a similar rise in sales or downloads. The store has removed terabytes of AI-generated spam and expanded rules requiring AI-use disclosures in several categories. (kotaku.com)
At an AI-native startup, engineer Neil Kakkar increased his monthly pull requests from 8-20 to more than 200. AI removed communication and review bottlenecks but brought new challenges, including context switching, lost shared understanding, and less attention to design. (newsletter.pragmaticengineer.com)
Today's best Hacker News stories, summarized and screenshotted, one email a day.