No single through-line today — the stories below are unrelated.
Issue signature
The Wire
- Langfuse VIII: The Playground Looked Fine. That Is Not a Langfuse Experiment.
- LangFuse VII: You Changed the Prompt Without a Deploy. You Still Cannot Tell If the Reply Is Any Good
- The World Won't Wait: Evaluating and Teaching Agents Under a Live Clock
- Evaluating Model Capabilities After Benchmark Saturation
- DeepSeek V4.1 Flash 1017 now available on AI Gateway
- Building trust in AI agents: A production-ready evaluation framework with Amazon Bedrock AgentCore
- How Itaú is building generative AI for its entire customer base
- Grounding AI agents in biological reality: Building blocks for autonomous wet labs
- Introducing Reflection Beam: an open-weight model for agentic coding on AWS
- Continuous accountability for Verified bots