Skip to content
All tags

#conversational-ai

2 posts

Stanford CS224V Lecture 1: Turning Hallucinating LLMs into Dependable Assistants

Fall 2025 opens with computational thinking: reliability comes from decomposing retrieval, formal representation, verification, and generation into testable algorithms, not from one heroic prompt.

ai deep-dive

Deepgram Voice Agent API: From Streaming STT and Turn Detection to TTS

Deepgram combines streaming STT, LLM orchestration, turn detection, barge-in, and streaming TTS over one WebSocket while preserving paths for standalone speech models and bring-your-own LLM or TTS.