WeRide Introduces WITT, a Physical AI Cognitive Foundation Model Built on Atomic Physical Facts
WeRide introduced WITT, a Physical AI Cognitive Foundation Model designed to build AI cognition of the physical world by extracting trusted facts from real-world operational data. The company claims WITT reduces token costs by up to 98% and delivers up to 200x greater data-processing efficiency compared to larger general-purpose AI models while achieving a factual error rate roughly one-third of competitors.
Key figures
- Dynamic tags per request
- more than 100
- Operational cities count
- 40
- Token cost reduction pct
- 98
- Autonomous vehicles count
- 3000
- Vehicle programs wrd3 count
- 30
- Data processing efficiency multiplier
- 200
- Factual error rate vs general purpose
- one-third
- Video processing capacity minutes per day
- 10000
AI analysis
The rest of the AI analysis, red flags and sentiment are part of Signal8 Pro.
AI-generated analysis of a public disclosure. Not investment advice; verify against the original document.