MicroZig to Adopt Strict No LLM / No AI Policy
MicroZig plans to adopt a strict ban on LLM and AI use. Its code of conduct covers the Zig Embedded Group’s GitHub organization and Discord server. (github.com)
Experiential is an open-source gateway and router that exposes a single OpenAI-compatible API to orchestrate hosted, BYOK, and local models for agent workflows. It lets teams centralize provider keys (OpenAI, Anthropic, Gemini, Azure, AWS Bedrock, Fireworks, OpenRouter), enforce who or which agent can call which models, set per-identity budgets, and route traffic for cost, latency, or quality goals. Deployable locally via pip and an exp CLI or used as a managed hosted gateway, it issues short-lived keys, supports both OpenAI-style chat completions and Anthropic Messages, and provides ready commands and code samples (curl examples, exp.load_router in Python) to start routing requests through a chosen public alias like opus-5.
The platform’s distinctive capability is turning observed agent traffic into optimized routing decisions and into improved models: collect OpenTelemetry traces (or use a public dataset), build a project router with exp build, then fine-tune or distill a fitted model with exp optimize model and Tinker to trade off speed, cost, and quality. Anonymous aggregate telemetry is enabled by default but excludes prompts, raw content, and credentials. Documentation, setup guides, and CI/dev tooling accompany the Apache-2.0-licensed codebase, which aims to give engineering teams a unified control plane for experimentation, governance, and production routing of multimodel AI workloads.
Summary generated by AI from the linked article. hn.today is not affiliated with Hacker News or Y Combinator.
MicroZig plans to adopt a strict ban on LLM and AI use. Its code of conduct covers the Zig Embedded Group’s GitHub organization and Discord server. (github.com)
Qwenputer embeds a deterministic RISC-V CPU in Qwen3.5 4B’s weights, using its Gated DeltaNet state as RAM to run arithmetic and code without external tools. The experiment also adds in-model file storage and is available with its code on Hugging Face and GitHub. (divagr.com)
The New York Times is adding more AI features to its Cooking app. Users have reacted negatively to the changes. (niemanlab.org)
Google’s AI-powered search gave some U.S. users no clear answer about who won the 2020 election, though Gemini answered correctly and Google appeared to fix the issue. The incident renews concerns about the company’s AI quality control, especially after similar failures in 2024. (karlbode.com)
Marissa Mayer drew criticism for saying her AI app helped describe her daughter in generic terms for a school presentation. The backlash reflects concerns that tech leaders are too detached from everyday life to understand how the public wants to use AI. (techcrunch.com)
Google AI Mode sometimes avoids directly saying Joe Biden won the 2020 US presidential election, instead directing users to official sources. Its responses vary across users and election years, while answers become more direct when asked outside the US. (arstechnica.com)
Today's best Hacker News stories, summarized and screenshotted, one email a day.