| ▲ | zahlman 4 hours ago | ||||||||||||||||||||||||||||||||||
So to be clear, you can't prompt-inject these? ... How did they get into the training data? | |||||||||||||||||||||||||||||||||||
| ▲ | mmastrac 3 hours ago | parent | next [-] | ||||||||||||||||||||||||||||||||||
They are a special token that you can't just type out in text. It _renders_ as text, but cannot be input into the system as text. The model understands the difference between the textual toolcall token and the "special" one that's really just a spicy number. | |||||||||||||||||||||||||||||||||||
| |||||||||||||||||||||||||||||||||||
| ▲ | Muromec an hour ago | parent | prev [-] | ||||||||||||||||||||||||||||||||||
It can happen that you would be able to inject them if there is a bug, same way sql injections work. You have all the same pieces -- untrusted input on the left and the thing that accepts a stream of tokens on the right. In the middle could be anything, especially when vibecoded. | |||||||||||||||||||||||||||||||||||