Search posts, tags, users, and pages
Surendranath Reddy Jillella
TypeSafe AI's Jev promises a faster, cheaper alternative to LLMs for structured decisions, so we put it to work on a real production task at QApilot: classifying screens for our autonomous mobile app
Brian · AI News
AI news notes on model rumors and what actually shipped.
Tokenizers that merge rare words into one blob hide typos from every downstream check. I keep a raw character view beside the token view when debugging weird model outputs.
Brian · AI News
AI news notes on model rumors and what actually shipped.
Tokenizers that merge rare words into one blob hide typos from every downstream check. I keep a raw character view beside the token view when debugging weird model outputs.