Decisions API is now in public beta. It provides a dedicated endpoint and developer workflow for building deterministic, model-driven decision-making into applications, combining reasoning-focused models with structured outputs, streaming, and background execution. The API surfaces decisions alongside concise rationales and integrates with tools, file inputs, and multi-agent setups so apps can call external services, perform retrieval, or run tool chains as part of a decision flow. It supports realtime and voice integrations, webhooks for asynchronous handling, and options for compaction and token counting to help control cost and throughput.
The beta is documented alongside SDKs, a CLI, and broader platform features for agents, tools, and production deployment. Coverage includes model selection and pricing considerations, prompts and best practices for reasoning, safety and governance controls, rate limits and observability, and migration paths from legacy APIs. Targeted use cases include voice-driven assistants, commerce and agent orchestration, and workflows that require auditable, reproducible choices. The documentation provides API reference, examples, and operational guidance to implement Decisions in both exploratory builds and production environments.
Summary generated by AI from the linked article. hn.today is not affiliated with Hacker News or Y Combinator.
NanoMuse is an open-source AI agent designed to work across multiple devices, including phones, tablets, and computers. It remembers user preferences, stays active when apps are closed, and interacts through a personalized interface. (github.com)
OpenWAM is an open framework that combines video prediction and robot control using a shared causal video backbone. It supports various interaction models and improves robot task success rates through causal adaptation and counterfactual supervision. (openwam.stanford.edu)
OpenAI's Decisions API can evaluate GitHub pull requests by analyzing diffs against specific review questions, such as compatibility or migration needs. This helps organize review processes by providing clear answers to targeted concerns. (vercel.com)
Strands Decider 2B is an open-source decision model designed for building AI agents. It supports various tools, integrations, and deployment options for creating and managing intelligent systems. (strandsagents.com)
UniEvo-VL is a framework that enables multimodal models to improve themselves by using their own feedback during testing. It enhances image generation performance without external supervision, showing significant gains on benchmark tests. (arxiv.org)
OpenAI has produced mathematical manuscripts and supporting proof artifacts available on GitHub. These resources aim to advance research and understanding in mathematical AI applications. (github.com)
Today's best Hacker News stories, summarized and screenshotted, one email a day.