Most likely there is a separate censor LLM watching the model output. When it detects something that needs to be censored it will zap the output away and stop further processing. So at first you can actually see the answer because the censor model is still “thinking.”
When you download the model and run it locally it has no such censorship.
what i don’t understand is why they won’t just delay showing the answer for a while to prevent this, sure that’s a bit annoying for the user but uhhhhh… it’s slightly more jarring to see an answer getting deleted like the llm is being shot in the head for saying the wrong thing…
Most likely there is a separate censor LLM watching the model output. When it detects something that needs to be censored it will zap the output away and stop further processing. So at first you can actually see the answer because the censor model is still “thinking.”
When you download the model and run it locally it has no such censorship.
what i don’t understand is why they won’t just delay showing the answer for a while to prevent this, sure that’s a bit annoying for the user but uhhhhh… it’s slightly more jarring to see an answer getting deleted like the llm is being shot in the head for saying the wrong thing…