Sublime

> We find that LLMs’ intelligence [...] almost linearly correlates with their ability to compress external text corpora > compression efficiency [...] serves as a reliable evaluation measure that is linearly associated with the model capabilities IQ for LLMs just dropped https://t.co/B9UOeLctRS

In ride hailing there is an interesting user behavior. When users book their ride, and the driver is not allocated in the first 20/30 secs, instead of waiting for the request to get timed out and the system showing driver not found, they just cancel and reorder. They feel the chances are hi... See more