The author implies that Grok 3 becoming racist because of a system prompt is a bad thing.
I think it's a good thing and shows how steerable the model is. Many other models pretty much ignore the system prompt and always behave the same.
I think it's a good thing and shows how steerable the model is. Many other models pretty much ignore the system prompt and always behave the same.
He didn't "become racist". Megahitler Grok defended completely opposite political opinions in different threads, just depending on what kind of trolling would be funnier. But unsurpringly, only "megahitler" because viral enough.
In general I agree that it's a desirable characteristic for a foundation LLM to behave according to developer instructions.
I didn't know Claude offered that capability. They probably have another model on top (a classifier or whatever) that checks the LLM output.