It may not be directly intentional, but it’s certainly a consequence of decisions xAI have taken in developing Grok. Without even knowing exactly what those decisions are, it’s pretty clear that they’re questionable.
Whether this instance was a coincidence or not, i can not comment on. But as to your other point, i can comment that the incidents happening in south africa are very serious and need international attention
Musk said "stop making it sound woke" after re-training it and changing the fine tuning dataset, it was still sounding woke. After he fired a bunch more researchers, I suspect they thought "why not make it search what musk thinks?" boom it passes the woke test now.
Thats not an emergent behaviour, that's almost certainly deliberate. If someone manages to extract the prompt, you'll get conformation.
I think Simon was being overly charitable by pointing out that there's a chance this exact behavior was unintentional.
It really strains credulity to say that a Musk-owned ai model that answers controversial questions by looking up what his Twitter profile says was completely out of the blue. Unless they are able to somehow show this wasn't built into the training process I don't see anyone taking this model seriously for its intended use, besides maybe the sycophants who badly need to a summary of Elon Musk's tweets.
The only reason I doubt it's intentional is that it is so transparent. If they did this intentionally, I would assume you would not see it in its public reasoning stream.
It may not be directly intentional, but it’s certainly a consequence of decisions xAI have taken in developing Grok. Without even knowing exactly what those decisions are, it’s pretty clear that they’re questionable.
Whether this instance was a coincidence or not, i can not comment on. But as to your other point, i can comment that the incidents happening in south africa are very serious and need international attention
I see what you did there :)
Of course its intentional.
Musk said "stop making it sound woke" after re-training it and changing the fine tuning dataset, it was still sounding woke. After he fired a bunch more researchers, I suspect they thought "why not make it search what musk thinks?" boom it passes the woke test now.
Thats not an emergent behaviour, that's almost certainly deliberate. If someone manages to extract the prompt, you'll get conformation.
I think Simon was being overly charitable by pointing out that there's a chance this exact behavior was unintentional.
It really strains credulity to say that a Musk-owned ai model that answers controversial questions by looking up what his Twitter profile says was completely out of the blue. Unless they are able to somehow show this wasn't built into the training process I don't see anyone taking this model seriously for its intended use, besides maybe the sycophants who badly need to a summary of Elon Musk's tweets.
The only reason I doubt it's intentional is that it is so transparent. If they did this intentionally, I would assume you would not see it in its public reasoning stream.
They've made a series of equally transparent, awkward changes to the bot in the past; this is part of a pattern.
Bold of you to assume people here read the linked post.