Internal documents reveal that the OpenAI Strawberry project enables AI to plan and navigate the internet autonomously, marking a significant step in AI research.
An OpenAI spokesperson commented on the company's broader research goals, stating, 'We want our AI models to see and understand the world more like we do...these systems will improve in reasoning over time.'
At a recent internal meeting, OpenAI demonstrated a project with new human-like reasoning skills, indicating significant progress in advanced reasoning research.
This post-training, or 'fine-tuning,' involves adapting base models with targeted feedback and examples of good and bad answers, similar to Stanford's STaR.
Collection
[
|
...
]