tomr75·el mes pasado·discusspeople who can't afford Claude max 200 are using qwen 3.6 27b for local coding assistance already
tomr75·hace 4 meses·discusspretty sure Nvidia GPU is better bang for buck because of usable inference speed..
tomr75·hace 9 meses·discussuse USD denominated stablecoins on a permissionless blockchain (any layer 2 ethereum network like arbritrum) or a ZK L2 ...
tomr75·hace 10 meses·discussjust reduce the services you provide Europeans, let the Europeans vote out these people
tomr75·hace 12 meses·discussit depends on how many people you expect to date in your lifetime thoughthese days with dating apps can prob date way more than 18..
tomr75·el año pasado·discusspresumably their apply model is run on their serversI wonder how hard it would be to build a local apply model/surely that would be faster on a macbook
tomr75·el año pasado·discussexpressive: https://github.com/resemble-ai/chatterboxdialogue like notebooklm: https://github.com/nari-labs/dia
tomr75·el año pasado·discusshow does it have access to DOM? are you using it with cursor/browser MCP?