Earlier today, we hosted our third CAST (Coffee And Showcase Tour) meeting, "LLMs in Research—What Works and What Doesn't," in Hong Kong. This followed similar small-group sessions in San Francisco and London last year.

Some of the hot topics were around the need for domain-specificity, proprietary data, human expertise as a key factor in tweaking LLM deployments, and deterministic rules augmenting LLMs.

Our use cases and experience at Robotic Online Intelligence (ROI) served as discussion triggers.

Next: Singapore, likely in the week of Feb 24.