notdevin

It would be great to know the weights of a model but that won’t happen. They could, however, give us abstracted coordinates that reference the training data relevant to produce an output which would help you discovery your own way to more precisely steer the output

@backpack put a bank in your pocket and use your money whenever, wherever, however without permission

/backpack
/notdevin
icebreaker.xyz/notdevin

I’ve read this multiple times. Can’t still make it out

Yes, when I put in a prompt and then get an output, I want to know abstractly where that came from, even better if I can get info on the nearest neighbor but if not self discovery is also fine, should only need to occur the first time or until the model is updated

Take it easy on me. I’m just trying to make friends. ❤️ | Data analysis | fitness 

https://warpcast.com/notdevin.eth/0xeffcdaee

It’s a bit anthropomorphic for my liking to say it that way but yeah. Said annoyingly, the training model is a representation of the collective intelligence that participated in creating the data. The average social input to the data should be represented as the fat part of the data curve. If I’m speaking novelty in my workflow, then it would be helpful to be able to discern that I’m sitting in the average part of the data right now

Think this one aims an answer in that direction

Think this one aims an answer in that direction

https://warpcast.com/notdevin.eth/0x7f75d06a

Oh now it makes sense. How do you think traceability will impact your interaction with ai models tho. Good or bad. Especially in tasks that precision is key.