RL fine-tuning
Reinforcement-learning-based fine-tuning of a model to improve its behavior on specific tasks.
As defined in Satya Nadella — How Microsoft is preparing for AGI
Where it comes up · 1
Most important claims · 2 of 2Search all claims for “RL fine-tuning” →
- Microsoft will use OpenAI models maximally across all products for the next seven years, adding value via RL fine-tuning and mid-training runs on the GPT family using unique data assets, while deliberately not duplicating those flops, and will simultaneously build its own MAI models for cost/latency-optimized or specialized capabilities.Satya Nadella — How Microsoft is preparing for AGI
- Microsoft's Excel Agent is not a UI-level wrapper but a model embedded in the middle tier of Office, taught the native artifacts and tools of Excel via markdown so it can natively understand formulas and fix its own reasoning mistakes—wrapping a cognitive layer around traditional business logic so Excel ships with an analyst bundled in.Satya Nadella — How Microsoft is preparing for AGI