MCP App StoreThe latest from the AI and MCP ecosystem, curated daily.
Sources
The system card for GPT-5.3 Instant details the model’s intended uses, safety mitigations, and benchmarked capabilities, giving developers guidance on guardrails and recommended system prompts. It’s a useful technical reference for teams integrating GPT-5.3 Instant into production systems and for evaluating suitability for specific tasks.
OpenAI and Amazon introduce a stateful runtime for agents in Amazon Bedrock that brings persistent orchestration, memory, and secure execution to multi-step AI workflows. This runtime aims to make agent-based applications more reliable and easier to build by preserving context and managing execution state. Developers building multi-step agents or long-running workflows on Bedrock should evaluate this for simplified orchestration and improved memory handling.
OpenAI's February threat report analyzes how malicious actors chain models with web platforms to scale harmful campaigns and evaluates detection and mitigation strategies. For developers and security engineers, the report highlights attack patterns to watch for and recommends instrumentation and model-safety practices to reduce exploitation risk. Implementing the recommended detection signals and provenance checks will help harden systems that integrate models.
OpenAI explains that SWE-bench Verified has become contaminated and mismeasures frontier coding progress, recommending SWE-bench Pro instead. This is significant for researchers and toolmakers building or evaluating coding models: benchmarks can mislead product decisions if they leak or poorly reflect real-world tasks. Developers should consider benchmark provenance and prefer evaluation suites with robust guardrails like SWE-bench Pro.
OpenAI shares reasoning proofs from their models tackling the First Proof math challenge. The results provide insight into the current limits and capabilities of research-grade AI reasoning on expert-level problems.
OpenAI and Paradigm launched EVMbench, a specialized benchmark for evaluating AI agents' ability to find and fix high-severity smart contract vulnerabilities. This provides a critical tool for improving agent reliability in secure coding and blockchain environments.
GPT-5.2 has successfully proposed a new formula for gluon amplitude in theoretical physics, which was subsequently verified by academic collaborators. This marks a significant milestone in LLMs contributing to frontier scientific discovery.
OpenAI introduced Lockdown Mode and Elevated Risk labels to protect organizations from prompt injection and data exfiltration. These features are essential for enterprises deploying AI in high-security environments.
OpenAI released GABRIEL, an open-source toolkit that uses GPT to convert qualitative text and images into quantitative data. This allows social scientists to analyze large-scale research datasets with high precision.
OpenAI details the engineering behind their real-time access system, integrating rate limits and usage tracking to scale Sora and Codex. Essential reading for developers building high-throughput AI infrastructure.
OpenAI launches GPT-5.3-Codex-Spark, a real-time coding model offering 15x faster generation and 128k context. Now in research preview for ChatGPT Pro users.
An exploration of how Codex is being utilized to build robust agentic workflows. Focuses on the engineering patterns required for an agent-first development environment.
OpenAI's GPT-5 combined with Ginkgo Bioworks' automation reduced cell-free protein synthesis costs by 40%. This demonstrates the power of closed-loop AI experimentation in biotechnology.
OpenAI Frontier is a new enterprise platform specifically for managing AI agents. It provides critical infrastructure for shared context, permissions, and governance at scale.
The GPT-5.3-Codex system card reveals the most capable agentic coding model yet. It integrates frontier coding performance with advanced reasoning and professional knowledge.
OpenAI introduces GPT-5.3-Codex, a native agent combining frontier coding performance with general reasoning. It is designed to handle complex, long-horizon technical tasks and real-world software engineering.
OpenAI details the Codex App Server, a bidirectional JSON-RPC API that enables embedding Codex agents. The system supports streaming progress, tool execution, and diff-based approvals for technical work.
OpenAI has launched the Codex app for macOS, providing a dedicated command center for AI-driven software development. It supports multi-agent coordination and parallel workflows for managing complex, long-running coding tasks.
OpenAI detailed its internal data agent leveraging GPT-5 and Codex to perform reasoning over massive datasets. The system emphasizes reliability and speed in delivering insights, showcasing advanced agentic memory and data processing patterns.
OpenAI is retiring GPT-4o, GPT-4.1, and o4-mini from ChatGPT as of February 13, 2026. Note that these changes currently apply only to the ChatGPT interface and do not affect API access.