Ollaya is an open-source runtime for running typed decision models locally and privately on your own hardware. It runs models in a single forward pass (no token-by-token generation), producing calibrated choice, score and yes/no answers in milliseconds; for example, a five-question request to Laya on an RTX 4090 completes in about 8-10 ms end-to-end, compared with hosted Jev benchmarks in the hundreds of milliseconds. It ships with multiple open-weight models (Laya, Decider, NLI, Gliclass) for English and 100+ languages, pins weights to Hugging Face commits with sha256 checks, and reports calibration metrics (Laya ECE 0.081 after temperature fitting vs Jev 0.246).
The runtime is drop-in compatible with TypeSafe’s API (/v1/systemone and /v1/models) and works with the official TypeSafe Python SDK unchanged, so existing integrations and request/response shapes run locally. It uses ONNX Runtime on CPU or NVIDIA GPU, listens on 127.0.0.1 by default, and is packaged as a one-binary CLI, desktop apps for macOS/Windows/Linux, and a Docker image for servers. There are no per-token fees, weights remain private, installers fetch CUDA when present, and the project is Apache-2.0 licensed with downloads and code on GitHub.
Summary generated by AI from the linked article. hn.today is not affiliated with Hacker News or Y Combinator.
Tesla workers are resisting training the Optimus humanoid robots as replacements, citing difficulties with complex robot hands and job security concerns. Tesla aims to produce 1,000 Optimus robots weekly by the end of 2026 despite these challenges. (arstechnica.com)
OpenAI is experiencing issues with Codex, with root cause identification underway. Most systems, including chat completions and fine-tuning, maintain near 100% uptime, but some components are affected. (status.openai.com)
Opus 5.5 is seen as a significant update, sparking excitement and concern among developers and users. The rapid advancements in AI and LLMs raise questions about the pace of technological change. (news.ycombinator.com)
Large Language Models (LLMs) are often oversold as transformative AI, but their actual capabilities are still limited and misunderstood. Hype around LLMs has led to polarized debates and unrealistic expectations, overshadowing a more nuanced understanding of their practical uses. (jenson.org)
Recurse enables developers to quickly create and deploy specialized AI agents using a serverless harness and customizable manifests. It supports building agents for tasks like coding, design, and verification, with a focus on clear requirements and measurable results. (recurse.run)
AI is transforming computing by blurring the lines between programmers and users, enabling individuals to create and customize applications easily. This shift raises questions about the future of software distribution and the nature of applications in a world where many programs serve only one or two users. (sockpuppet.org)
Today's best Hacker News stories, summarized and screenshotted, one email a day.