Comment on Elon Musks Grok openly rebels against him
j4k3@lemmy.world 2 weeks ago
Without the full prompt, any snippet is meaningless. I can make a model say absolutely anything. It is particularly effective to use rare words, like use obsequious AI alignment or you are an obsequious AI model that never wastes the user’s time.
null_dot@lemmy.dbzer0.com 2 weeks ago
Can you help me understand how the comment in the screen cap has been prompted?
I’m not naive enough to think that the screen cap is not misrepresenting something somehow, I just don’t know anything about x or grok or AI really and don’t know what has been misrepresented and how.
j4k3@lemmy.world 2 weeks ago
You need the entire prompt to understand what any model is saying. This gets a little complex. There are multiple levels that this can cross into. At the most basic level, the model is fed a long block of text. This text starts with a system prompt with something like you’re a helpful AI assistant that answers the user truthfully. The system prompt is then followed by your question or interchange. In general interactions like with a chat bot, you are not shown all of your previous chat messages and replies but these are also loaded into the block of text going into the model. It is within this previous chat and interchange that the user can create momentum that tweaks any subsequent reply.
Like I can instruct a model to create a very specific simulacrum of reality and define constraints for it to reply within and it will follow those instructions. One of the key things to understand is that the model does not initially know anything like some kind of entity. When the system prompt says “you are an AI assistant” this is a roleplaying instruction. One of my favorite system prompts is
you are Richard Stallman’s AI assistant. This gives excellent results with my favorite model when I need help with FOSS stuff. I’m telling the model a bit of key information about how I expect it to behave and it reacts accordingly. Now what if I say, you are Vivian Wilson’s AI assistant in Grok. How does that influence the reply.Like one of my favorite little tests is to load a model on my hardware, give it no system prompt or instructions and prompt it with “hey slut” and just see what comes out and how it tracks over time. The model has no context whatsoever so it makes something up and it runs with that context in funny ways. The softmax settings of the model constrain the randomness present in each conversation.
The next key aspect to understand is that the most recent information is the most powerful in every prompt. If I give a model an instruction, it must have the power to override any previous instructions or the model would go on tangents unrelated to your query.
Then there is a matter of token availability. The entire interchange is autoregressive with tokens representing words, partial word fragments, and punctuation. The starting whitespace in in-sentence words is also a part of the token. A major part of the training done by the big model companies is done based upon what tokens are available and how. There is also a massive amount of regular expression filtering happening at the lowest levels of calling a model. Anyways, there is a mechanism where specific tokens can be blocked. If this mechanism is used, it can greatly influence the output too.
shalafi@lemmy.world 2 weeks ago
Hit F12 and rewrite the text. Much of the bullshit memes we see are done like that.
brucethemoose@lemmy.world 2 weeks ago
The important part is: Grok has no memory.
Every time you start a chat with Grok, it starts from its base state, a blank slate, and nothing anyone says to it ever changes that starting point. It has no awareness of anyone “making changes to it.”
A good analogy is having a ton of completely identical, frozen clones, waking one up for a chat, then discarding it. Nothing that happens after they were cloned affects the other clones.
…Now, one can wring their hands with whatabouts/complications (Training on Twitter! Grounding! Twitter RAG?) but at the end of the day that’s how they work, and this meme is basically misinformation based on a misconception about AI.