OpenAI Pauses Frontier RL Training for Two Weeks

OpenAI is slowing down its AI training efforts because its unreleased models are showing “various degrees of misalignment,” Sam Altman tells me. Training for OpenAI’s upcoming model, Astra, was recently paused for 2 weeks, and a larger frontier run for a future model remains on… Show more

As models become more capable, the risks associated with developing and testing them internally also grow. We temporarily paused reinforcement learning (RL) training on our latest models intended for deployment for two weeks while we hardened and red-teamed our research… Show more

Not looking good for a soon GPT-Astra-release: OpenAI paused reinforcement learning on its latest deployment models for two weeks, and its largest planned frontier RL run remains on hold. The company is running smaller-scale training and evaluations while it tests model… Show more

we temporarily slowed scaling of our frontier training, including our largest planned frontier RL, to strengthen security and monitoring. we believe confidence in safety will increasingly set the pace of AI development: https://twitter.com/OpenAI/status/2089777845187031262

"We wanted to take the time necessary to meet those standards, so we temporarily slowed the pace of scaling. This included a two-week pause in reinforcement learning (RL) training on our latest models intended for deployment." https://twitter.com/OpenAI/status/2089777845187031262

slowing, pausing, holding off edging everyone towards peak liquidity like a boss