
OpenAI has unveiled GPT-Live 1 alongside a dedicated Agent API, allowing developers to build real-time voice applications and autonomous agents. The GPT-Live feature enables low-latency voice conversations, while the Agent API provides tools for creating AI agents that can perform multi-step tasks. This move significantly lowers the barrier for building interactive AI experiences.
Read original
© Matt WolfeGoogle updates Gemini 3.8 with Live Avatar technology and advanced Text-to-Speech capabilities.
© Matt WolfeMicrosoft introduces a new version of Copilot featuring 'Home Code' and 'Autopilot' capabilities for enhanced productivity.
© Matt WolfeThe new Agents API enables developers to build agents that retain memory and progress between sessions.
This release stabilizes Claude Code by fixing a cascade of session-breaking errors that previously caused silent data loss or API drops. The most significant fix addresses resumed conversations re-sending messages in altered forms, which was corrupting reasoning traces and breaking extended thinking workflows. It also resolves persistent login refresh loops and managed setting parsing failures that plagued enterprise deployments. While the changelog is dense with UI tweaks like scrollbar fixes and vim mode corrections, the core value lies in restoring reliability for long-running agent sessions.
This release quietly solves a major pain point for enterprise AI workflows by adding gateway hint headers, allowing LLM gateways to correctly group requests per user prompt instead of treating them as isolated events. The new managed settings for availableModelsMatch and deniedModels give organizations precise control over model access, blocking specific versions even when broader allowances exist. Beyond governance, the update stabilizes the plugin ecosystem with rigorous validation checks that prevent silent failures from broken or misconfigured extensions. These changes shift Claude Code from a developer tool to a manageable enterprise component.
This release quietly refactors how llama.cpp handles Flash Attention on Apple Silicon by splitting kernels into per-dtype libraries. It’s a structural optimization that likely reduces memory overhead and improves compilation times for Metal users, though the immediate performance gains are subtle compared to algorithmic leaps. The build matrix remains massive, adding ROCm 10.0 and CUDA 13.4 support while disabling KleidiAI on Apple Silicon for now. This is infrastructure maintenance rather than a feature breakthrough, but it keeps the runtime robust across the expanding landscape of hardware backends.