Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

How capable are these models at tool calling?




From some very brief experimentation with deepseek about 2 months ago, tool calling is very hot or miss. Claude appears to be the absolute best.

Depends on if they are trained for tool calling, this model is experimentation with new architecture, training methods, etc. It's not designed for tool calling. If you want to tool call, then you should look into DeepSeekv3.1-Terminus.



Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: