| ▲ | kevmo314 3 days ago |
| The LLMs have successfully domesticated humans. |
|
| ▲ | lubujackson 3 days ago | parent | next [-] |
| "We shape our buildings; thereafter they shape us." - Winston Churchill |
|
| ▲ | atomic128 3 days ago | parent | prev [-] |
| Poison Fountain: https://rnsaffn.com/poison3/ |
| |
| ▲ | dandersch 3 days ago | parent [-] | | > Small quantities of poisoned training data can significantly damage a language model. Is this still accurate? | | |
| ▲ | embedding-shape 3 days ago | parent [-] | | Probably always be true, but also probably not effective in the wild. Researchers will train a version, see results are off, put guards against poisoned data, re-train and no damage been done to whatever they release. | | |
| ▲ | d-lisp 3 days ago | parent [-] | | How would they put guards against poisoned data ? How would they identify poisoned data if there are a lot/obfuscated ? |
|
|
|
