Comment by utilize1808
7 days ago
You can prove an open source implementation of a cryptography algorithm to be backdoor free. You can’t do that with open weight models.
7 days ago
You can prove an open source implementation of a cryptography algorithm to be backdoor free. You can’t do that with open weight models.
Even if you cannot know what is in an open-weights LLM, so it may include malicious content, it is still infinitely safer to run yourself an open-weights LLM, regardless who made it, when you can control as finely as you want its actions and you can customize token probability sampling, than to subscribe to an LLM as a service provided by an external company.
Easier said than done. Manipulating sampling probability is almost certainly detrimental to model performance.