You can now fine-tune your enterprise’s own version of OpenAI’s o4-mini reasoning model with reinforcement learning

You can now fine-tune your enterprise’s own version of OpenAI’s o4-mini reasoning model with reinforcement learning

For organizations with clearly defined problems and verifiable answers, RFT offers a compelling way to align models.

Early-stage startup Theta claims edge over OpenAI Operator

Y Combinator-backed startup Theta Software, which builds self-learning and real-time adaptation for AI agents, has recently launched. The startup claims it is starting with an intelligent memory layer so that agents can remember and learn from previous interactions. This memory layer uses real-time reinforcement learning (RL) to analyze every run for mistakes and optimizations with a simple four-line addition to existing code. According to Theta…

OpenAI adds new fine-tuning options for o4-mini and GPT-4.1

OpenAI is expanding its fine-tuning program for o4-mini, introducing Reinforcement Fine-Tuning (RFT) for organizations. The method is designed to help tailor models like o4-mini to highly specific tasks with the help of a programmable grading system. The article OpenAI adds new fine-tuning options for o4-mini and GPT-4.1 appeared first on THE DECODER.

OpenAI introduces Reinforcement Fine-Tuning (RFT) for organizations. The method is designed to align AI models like o4-mini more precisely to specific tasks – with the help of a programmable evaluation system. The article OpenAI extends Fine-Tuning methods for AI models o4-mini and GPT-4.1 first appeared on THE-DECODER.de.

OpenAI opens the door to reinforcement fine-tuning for o4-mini

With RFT, OpenAI offers organizations more control when deploying AI, without the need for specialized AI teams.

OpenAI Releases Reinforcement Fine-Tuning (RFT) on o4-mini: A Step Forward in Custom Model Optimization

OpenAI has launched Reinforcement Fine-Tuning (RFT) on its o4-mini reasoning model, introducing a powerful new technique for tailoring foundation models to specialized tasks. Built on principles of reinforcement learning, RFT allows organizations to define custom objectives and reward functions, enabling fine-grained control over how models improve—far beyond what standard supervised fine-tuning offers. At its core, RFT is designed to help devel…