GoKawiilOpenAI’s GPT-5 turns one tomorrow, and the company is marking the week by looking beyond individual models. Today, OpenAI introduced Agent Plugins, an open standard meant to let reusable AI-agent extensions work across compatible products.
GPT-5’s first year
GPT-5 launched August 7, 2025, replacing GPT-4o and several reasoning models as ChatGPT’s default. Its defining feature was automatic routing: ChatGPT could answer quickly or invoke deeper reasoning depending on the request. OpenAI also claimed fewer factual errors than GPT-4o.
Apple adopted the model with iOS 26, iPadOS 26, and macOS Tahoe 26. ChatGPT requests passed through Apple Intelligence, including Siri handoffs, Writing Tools, and visual intelligence, switched from GPT-4o to GPT-5.
GPT-5.1 promised warmer, more natural answers in November. December’s “code red” GPT-5.2 accelerated professional work in response to Gemini. GPT-5.3 Instant targeted ChatGPT’s “cringe” tone, followed two days later by GPT-5.4 Thinking with a million-token context window and built-in computer use.
OpenAI subsequently added GPT-5.4 mini and nano, the restricted GPT-5.4-Cyber, GPT-5.5 for more autonomous work, GPT-5.5 Instant, and July’s GPT-5.6 Sol, Terra, and Luna models.
From the Codex Mac app to a new ChatGPT
The software around those models transformed too. OpenAI launched a dedicated Codex Mac app in February as a hub for running multiple coding agents, reviewing changes, and scheduling work.
In July, Codex effectively became the new ChatGPT desktop app, combining Chat, Work, and Codex while the previous native client was renamed ChatGPT Classic.
For me, Codex has changed how I work with ChatGPT the most. I’m able to offload a lot more work that doesn’t require critical thinking and even build tools on my Mac that I couldn’t put together otherwise.
... continue reading