How to build an AI agent: A simple guide for anyone
The post How to build an AI agent: A simple guide for anyone appeared first on Source.
All articles
Filter publications by source, category, topic, language or date range.
1 618 articles · 1525–1536 displayed
Improving Fable 5's safeguards
We’re making updates to Claude Fable 5’s biology safeguards in a way that substantially reduces false positives. Fable 5 users will now experience many fewer “fallbacks”—where the system switches to a less capable model after they make a biology-related…
Baseten on Hugging Face Inference Providers 🔥
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
Teaching AI to speak the language of pathology
The post Teaching AI to speak the language of pathology appeared first on Source.
Introducing Shieldstral.
Shieldstral introduces a 3B open-weights multimodal safety classifier that outperforms models up to 7x its size.
Tino Cuéllar joins as Chief Global Affairs Officer
Mariano-Florentino (Tino) Cuéllar will join Anthropic as its first Chief Global Affairs Officer, leading the company’s work on policy, strategic international engagement, and government relationships worldwide. Tino’s career spans law, technology…
Orchard: An open framework for scalable agentic AI
Orchard is an open-source framework for the research community to train and evaluate AI agents across task types. It reduces complexity while supporting strong performance from smaller models by enabling researchers to reuse the same infrastructure. The post…
Echoverse: Deep, evolving environments for computer-use agents
Computer-use AI agents struggle with multi-step workflows like email and customer support. Echoverse trains agents in realistic environments rather than simply providing more training tasks, helping them improve as the tasks, tests, and environments evolve…
