MCP App StoreLe meilleur de l'écosystème IA et MCP, sélectionné chaque jour.
Sources
OpenAI enables real-time monitoring and steering of Codex coding tasks via the ChatGPT mobile app. Allows developers to approve and manage remote environments on the go.
OpenAI details the architecture of a secure Windows sandbox for Codex. This implementation ensures coding agents operate with strict file access and network restrictions to prevent unsafe system modifications.
OpenAI outlines its response to the TanStack npm supply chain attack and provides critical security updates for macOS users. The post details protections implemented to secure signing certificates and system integrity.
Insights from a massive community experiment exploring AI-assisted ML research. The project highlights the effectiveness of coding agents in quantization and novel model design under strict constraints.
OpenAI details the security architecture for running Codex, focusing on sandboxing, strict network policies, and agent-native telemetry. These measures ensure safe and compliant adoption of coding agents in production environments.
OpenAI introduces GPT-5.5 and a specialized Cyber variant to accelerate vulnerability research. This expansion of Trusted Access provides verified defenders with enhanced tools to protect critical infrastructure.
New realtime voice models are now available in the OpenAI API, bringing integrated reasoning, translation, and transcription. These updates enable developers to build more fluid and natural voice-based AI experiences.
OpenAI releases GPT-5.5 Instant as the new default model for ChatGPT. The update brings improved accuracy, reduced hallucinations, and more granular personalization controls for users.
OpenAI has released MRC (Multipath Reliable Connection) via the Open Compute Project. This new networking protocol enhances resilience and performance for massive AI training clusters by improving how data is routed across supercomputer networks.
OpenAI details the architectural overhaul of its WebRTC stack to support real-time Voice AI. The new system focuses on low latency and seamless conversational turn-taking at a global scale.
OpenAI explores the underlying causes and fixes for personality-driven quirks in GPT-5. This research provides insight into model behavior alignment and the technical challenges of scaling next-gen LLMs.
An analysis of how personality-driven quirks and 'goblin outputs' emerged in GPT-5 behavior. It details the timeline, root causes, and the fixes implemented to stabilize model personality.
OpenAI GPT models, Codex, and Managed Agents are now available on AWS, providing enterprises with a secure environment to deploy AI agents on their own infrastructure.
OpenAI introduces Symphony, an open-source specification for Codex orchestration. It enables the transformation of issue trackers into autonomous agent systems to reduce developer context switching.
OpenAI has released GPT-5.5, featuring significant improvements in speed and reasoning capabilities. The model is specifically optimized for complex coding, deep research, and multi-tool data analysis.
OpenAI introduces a guide on Codex plugins and skills for automating repeatable workflows and tool integration. This provides a framework for developers to build more reliable, data-driven agentic task completion.
A foundational guide to setting up Codex workspaces, managing projects, and executing tasks. Essential for developers onboarding to the Codex ecosystem to optimize their AI-assisted coding workflow.
OpenAI introduces Codex, a tool designed to automate complex tasks by connecting various tools and producing concrete outputs like documentation and dashboards. It moves beyond simple chat to a more agentic, output-oriented workflow.
OpenAI has launched a red-teaming challenge for GPT-5.5 focusing on biological safety risks. Researchers can earn up to $25,000 for finding universal jailbreaks that could lead to bio-safety breaches.
Deep dive into optimizing the Codex agent loop using WebSockets and connection-scoped caching. This approach significantly reduces API overhead and model latency, enabling faster, more responsive agentic workflows.