NVIDIA NeMo SteerLM is essentially a large language model (LLM) that can be used to help non-player characters (NPCs) in games respond with more personality and emotion. Many popular games today pack dozens of NPCs that mechanically repeat prerecorded text, regardless of the scenario.
When SteerLM is used in enterprise cases, a company could design a single chatbot around the model can tailor it in real-time based on the customers’ changing attitudes, demographics or circumstances. Lawyers can modify their SteerLM model during inference to adopt a formal style for their legal communications when necessary.
- NVIDIA Ampere Streaming Multiprocessors: The building blocks for the world’s fastest, most efficient GPU, the all-new Ampere SM brings 2X the FP32...
- 2nd Generation RT Cores: Experience 2X the throughput of 1st gen RT Cores, plus concurrent RT and shading for a whole new level of ray tracing...
- 3rd Generation Tensor Cores: Get up to 2X the throughput with structural sparsity and advanced AI algorithms such as DLSS. Now with support for up to...
I woke up early one morning with this idea, so I jumped up and wrote it down. It’s a challenging field, a kind of holy grail for making AI more closely reflect a human perspective — and I love a new challenge,” said Yi Dong, an applied research scientist at NVIDIA.
