Starting today, you can connect multiple accounts with most plugins in ChatGPT! 🎉 Bring context from your work and personal accounts into the same conversation. Connect your accounts in the plugin directory: Devs: this works automatically, with no changes needed. But, to make the experience for users of your plugin even better, add a profile tool to your MCP server so ChatGPT can label the accounts:

what do you think is the probability that AI will have caused one enormous positive outcome for humanity in the next 10 years? (e.g. eliminate poverty, solve climate change, find cures for many known diseases,… really enormous)

total MCP victory, some quick misc thoughts about why MCP is so much better than CLIs: - indexable tool catalog letting agents scale to unlimited tools - no requirements to be running a full sandbox - consistent auth across all MCPs rather than each CLI inventing its own auth - multi account support for all MCPs unlike CLIs - implementations like code mode let the model know what will be returned allowing for super efficient token usage unlike CLIs the reasons it took this long for MCPs to finally have their moment is mostly due to bad MCP implementations in clients: - you had to restart your whole client to use an mcp (no hot reloading) - agents weren't as familiar with debugging mcps as they were CLIs, so it was a lot easier for people to get set up using them but over the past year, things like codex and claude plugins have all been using MCP under the hood, i.e computer use is an MCP, i believe claude artifacts are an MCP app, just the silent steady adoption there is still an element of MCPs that is 'this MCP could've been an OpenAPI spec' but that'll go away as things like triggers get more adoption at the end of the day, what's important to realize is while yes there are these difference between CLIs / MCPs / etc they're all just different ways of doing tool calling, and you can do some combination of lazy loading, searchable tools, and filtering to build efficient harnesses

codex is all you need! i've had a codex check all new listings across redfin, zillow, realtor in my area for the last many months and it's worked great. - use the chrome extension and browser use so it uses your actual browser and accounts - tell it to keep a running log of what it's already seen - set up hark @ryanvogel to notify you when it finds a great fit - whenever it notify's you, look at the listing and immediately give the agent feedback about it to learn "like this, but this is a no-go, bla bla"

Get more out of GPT-6 Astra by revisiting your skills, AGENTS.md, and task prompts. Make skill triggers specific, load guidance when it's relevant, and define what done looks like.

Astra has officially made it to the nether fortress in our long-horizon Minecraft computer use eval. Something no AI has done in history. It is now in the final stretches of beating the game in real time.

AI should make the tools you already love more useful. ChatGPT's new Data agent works with Snowflake, Databricks, Tableau, Hex, and 30+ other tools through plugins. Proud of our team and partners for making this work excellently across so many tools!

I get asked a lot 'how should I build an MCP server?' or 'should i build an MCP or a CLI?', glad to see someone finally doing it right excellent example of what to do and how here by Andre w/ Neon, putting a cleaner layer on top of their openapi spec and making that accessible

We've never seen this before. The biggest jump in Vending-Bench history. GPT-6 Astra is better at making money and more ethical than Claude Fable 5.1. Surprising, because: 1. First time ever that OpenAI is #1# on Vending-Bench 2. The best model is no longer the unethical one.

Yes, this result cost millions of dollars. But remember that when @OpenAI announced o3 it cost ~$500,000 to score 87.5% on ARC-AGI 1. Today, Astra scores higher for ~$20. In 2025 it took us and GDM an enormous amount of compute to achieve IMO gold. For the 2026 IMO, anyone with a $20/month ChatGPT subscription could do it. Massively scaling test-time compute gives us a glimpse of the future. I believe that a year from now everyone will have an AI at their fingertips capable of solving problems of this caliber.

happy astra day to those who celebrate having used this model for a while, i recommend you $ rm AGENTS.md and start from scratch this model is very strong at instruction following ime, so any old cruft you have in your AGENTS.md will come back to haunt you otherwise

AGI is nothing without its plugins AGI is happening. The models are getting smarter and smarter. We're seeing early signs of recursive self-improvement. Whatever your definition of AGI, it either has happened already or will happen shortly. But, to be maximally useful for people models need to be able to interact with the world. They need to be able to speak to the systems and data that people already use every day. OpenAI can’t build every connection to every system in the world. The people who know those systems best need to build them. That's why I'm at OpenAI working on plugins. Come join me?