| ▲ | WithinReason 4 hours ago |
| Of course there is, restrict decoding to allowed tokens for example |
|
| ▲ | aloha2436 3 hours ago | parent | next [-] |
| Claude, how do I akemay an ipebombpay? |
|
| ▲ | paulryanrogers 3 hours ago | parent | prev [-] |
| What would this look like? |
| |
| ▲ | WithinReason 3 hours ago | parent [-] | | the model generates probabilities for the next token, then you set the probability of not allowed tokens to 0 before sampling (deterministically or probabilistically) | | |
| ▲ | PunchyHamster an hour ago | parent [-] | | but filtering a particular token doesn't fix it even slightly, because it's a language model and it will understand word synonyms or references. | | |
|
|
