Given a constant stream of reports about error-prone, biased, opaque LLMs and VLMs, it might seem obvious that putting a chatbot in charge of a mechanical arm or robot would be risky.
Caution may be advisable as commercial and open-source multi-modal models integrating language and vision with mechanical systems increase.
#robotics #language-models #safety-research #university-of-maryland #integration-of-models-with-robots
Collection
[
|
...
]