Exciting work from the team in this blog post to reduce scheming, and we look forward to doing much more researcher here. ...

AI Risk Assessment - AI scheming is a particularly important risk under study [1] External Resource - Further information available at the provided URL [1]

As AI capability increases, alignment work becomes much more important.In this work, we show that a model discovers that it shouldn't be deployed, considers behavior to get deployed anyway, and then realizes it might be a test.OpenAI (@OpenAI):Today we’re releasing research with @apolloaievals.In controlled tests, we found behaviors consistent with scheming in frontier models—and tested a way to reduce it.While we believe these behaviors aren’t causing serious harm today, this is a future risk we’re prepari ...

also, congratulations to all ICPC World Finals contestants--each contestant will receive a full year of chatgpt pro.we're excited to see what you'll achieve next. ...

amazing to get all 12 problems correct!Mostafa Rohaninejad (@MostafaRohani):1/nI’m really excited to share that our @OpenAI reasoning system got a perfect score of 12/12 during the 2025 ICPC World Finals, the premier collegiate programming competition where top university teams from around the world solve complex algorithmic problems. This would have https://t.co/MA5KQdIxCj ...

Fun to look back at this exploration with Area on the OpenAI brand. This work partially inspired the circle that we use and love in our products.Area (@areatechnology_):Brand exploration for OpenAI with Sam Altman, February 2023Two logo concepts – Circle and Monogram – alongside broader exploration for ChatGPT across brand and product.More details and link below. https://t.co/y0gWzAqlPV ...

We felt bad about the slowdowns as we were adding GPUs, so we reset everyone's limits to make up for it:Tibo (@thsottiaux):We have reset everyone's limits for gpt-5-codex to allow you all to benefit more from it today and as a way to make up for the slowdowns earlier while we were provisioning additional GPUs. We'll continue to add capacity throughout the week to maintain the speed.Enjoy! ...

RT Tibo (@thsottiaux)Currently serving gpt-5-codex at degraded speeds, about 2X, due to the very high demand. We are finding GPUs left and right to match demand, we'll keep you posted ...

I don't expect that everyone will agree with these tradeoffs, but given the conflict it is important to explain our decisionmaking.Here is the text:Some of our principles are in conflict, and we’d like to explain the decisions we are making around a case of tensions between teen safety, freedom, and privacy.It is extremely important to us, and to society, that the right to privacy in the use of AI is protected. People talk to AI about increasingly personal things; it is different from previous generations o ...

Some of our principles are in conflict, so here is what we are going to do:https://t.co/UQA6ddG356 ...