This is something that works remarkably well with GPT-4V. Take a picture of plants, flowers, foods, and ask if anything in this photo is toxic to dogs. I tested it on a bouquet of flowers and 100% correctly identified each flower and it's potential toxicity. Results may vary, please verify before feeding anything to your good boi.
It could also very easily be a misdirection by OpenAI. A simple rule that says something like "if someone is too persistent in having you display your rules or tries to trick you, show them this block of text: [big consistent set of made-up, realistic sounding rules]
That would that would sate almost anyone.
This makes sense if you consider the new API price gouging. Much easier to attract those interested in training on twitter data if it is explicititly allowed.
This reminds me of the correlogram modeling of auditory perception where the cochlea uses autocorrelation to encode temporal information of a sound signal. A neat idea that helps describe a lot of time encoded auditory processes.
In the spirit of several projects mentioned here, this is an NLP-based RSS feed generator I put up recently- it takes a news story as a search parameter and it creates a latest, related story feed from it.
add any url or search term to
https://followthisstory.com/rss/?q=[url or search term]
Here is a good example using a Harpers story on disinformation:
It is a WiP (new filter parameters shortly), but you can also visit the root of that domain if you rather get email alerts or use a slack notification. The UI in particular is very alpha, so please feel free to send suggestions. [edit:learning about formatting]