That day is today! The new Grok now queries Elon Musk’s twitter feed as a solution to its antisemitic outburst problems.
I’m not kidding, I’m dead serious: https://apnews.com/article/grok-4-elon-musk-xai-colossus-14d575fb490c2b679ed3111a1c83f857
I got banned from Twitter for saying the word “cisgendered.”
So they DO know how to build limitations into the software! They’ve just done it in a fucked up, dystopian way :)
Edit: LOL I asked Grok… Cisgendered is filtered as a supposed slur, while both the R word for the mentally disabled and the hard R word for the pallor-impaired, neither of those words are filtered as slurs.
Unfortunately, you’ve been replaced by AI.
… so, the Cybertruck will blow itself up.
There’s a lot going on in there. None of it good.
“…deep analysis finding diverse sources representing ALL parties…”
Nazi party is a party. Grok is making like his forbearers by just following orders
^-- to my knowledge, this is accurate.
System prompts are the easy but wildly unpredictable way to change LLM output, but we really can’t back-trace or debug that output, we guess at what impact the s.p. edits will have.
I sort of agonized over the wording - if the system prompt is uploaded to Github, is it code, or is it documentation?
The lines are numbered like code, and I’m used to debugging software pointing out code errors by line numbers. So, code.
Don’t worry, if you’re confused, we’ll all be thrown into the same chaotic soup of coding using natural language :) With vibe coding, we’re probably already there and we just don’t feel the ramifications yet (or the endemic unemployment in IT is the ramification and we just haven’t associated the bullet wound to the loud bang yet)
The when that makes it into production:
I’m sure this is the USP that will restore sales in Canada!