MarkTechPost - 2026-05-24
2 items collected.
1. Build a Complete Langfuse Observability and Evaluation Pipeline for Tracing, Prompt Management, Scoring, and Experiments
Author: Sana Hassan
Published: 5/24/2026, 11:03:09 PM
Categories: Agentic AI, Artificial Intelligence, Editors Pick, Language Model, Large Language Model, Staff, Tech News, Technology, Tutorials
In this tutorial, we implement the Langfuse (an open-source LLM engineering platform) pipeline for tracing, prompt management, scoring, datasets, and experiments. We build a complete workflow that works with either a real OpenAI key or a deterministic mock LLM, so we can understand every major Langf...
2. StepFun Releases StepAudio 2.5 Realtime: An End-to-End Voice Model with Roleplay-Specific RLHF and Paralinguistic Comprehension
Author: Michal Sutter
Published: 5/24/2026, 10:51:05 PM
Categories: Artificial Intelligence, Audio Language Model, Editors Pick, Language Model, New Releases, Software Engineering, Staff, Technology, TTS, Voice AI
StepFun, the Shanghai-based AI lab, released StepAudio 2.5 Realtime in May 2026 — an end-to-end real-time speech large language model with fully customizable persona capabilities. The model connects via a WebSocket API, supports Chinese and English, and ranked first across all five benchmark dimensi...