| ▲ | jstummbillig 2 hours ago | |
> And this tells you something important about what these systems are actually doing. It mostly tells me something about the things you presume, which are quite a lot. For one: That this is real (which it very well might be, happy to grant it for the purpose of this discussion) but it's a noteworthy assumption, quite visibility fueled by your preconceived notions. This is, for example, what racism is made of and not harmless. Secondly, this is not a systems issue. Any SOTA LLM can trivially be instructed to act like this – or not act like this. We have no insight into what set of instructions produced this outcome. | ||
| ▲ | Kim_Bruning an hour ago | parent [-] | |
> We have no insight into what set of instructions produced this outcome. https://github.com/crabby-rathbun Found them! | ||