So many prompts I have tried yet the results from Bing are always pretty weak compared to the real gpt-4. I also prompted it to write some Russian poems, so far it only spewed out gibberish with no rhymes. On the other hand, the real gpt-4 can sometimes produce really impressive shit, that I read with interest.

Another thing I noticed is that if I try to get Bing to generate something inappropriate, it'll go along and do it for a second, but then it'll quickly wipe its message. That's interesting because it suggests that the underlying model isn't the same as OpenAI's, which seems unable to generate harmful content at the core.

Isn't it?

Not to say you can find anything from a Molotov cocktail recipe to nude celebs with some trickery

Hi there! I'm trying to find a good not necessarily note-taking app, something like Joplin or Notion (sluggish and doesn't fit). There I could create a grid of images with captions, without having to use a whiteboard or anything too complex.

So, I've heard that ML manipulates tokens and specifically for the English corpora they take place of words. If we want model to be polite and not to speak uncomfortable language we can remove certain words from the internal array where all tokens and their associative data are stored, for example "fuck".

In the context of VPNs for example. Some VPNs store and provide information about what sites you go to third parties. Third parties analyze it and figure out what adds to show you. Hmm... then let them show me those adds they want to show me. I do hate adds as a whole and use an add blocker, thus. But I couldn't care less what particular type of adds they show me, they are still adds.

Someone knows what sites I go, what then. If someone curiously inquired me on this type of information I'd tell them without giving a second thought. Incomparably larger amount of data I put out just by making comments and posts.

How is it that devs decided to roll out it lacking basic functionality