Or replaced. If you make an automation tool to work more efficiently, it will be fun at first, but then you get fired because your job is no longer needed.
If I understand LLMs right, they have a maximum prompt length, but can be trained on any amount of text data.
The only way to add knowledge that doesn’t fit into a prompt, is to put it in the training data then re-train.
But, you could describe some sort of algorithm that it can use to sleuth out data using API calls, and it would then have access to lots more up-to-date data than can fit in a prompt. Except the body of the response would all have to become part of a prompt.
But the whole dataset it has access to doesn’t have to be mentioned in the conversation, so doesn’t have to be part of the prompt. Ultimately you don’t want your AI assistant telling you everything it knows in each interaction, just to access some slice of your data world, make changes to it, then eventually get you an answer or a report.
My sister had a marketing gig that she got let go of, because she was so good at selling her product that the company said they established strong markets in her area and didn’t need the publicity anymore.
Exactly that: too good at her job.
Or replaced. If you make an automation tool to work more efficiently, it will be fun at first, but then you get fired because your job is no longer needed.
That’s why you never tell anyone.
“I’ve automated my slack communications using GPT-4. Let’s see if anyone notices”
Classic Carl
Gotta do the freegpt and train it on your files, folders and messages.
If I understand LLMs right, they have a maximum prompt length, but can be trained on any amount of text data.
The only way to add knowledge that doesn’t fit into a prompt, is to put it in the training data then re-train.
But, you could describe some sort of algorithm that it can use to sleuth out data using API calls, and it would then have access to lots more up-to-date data than can fit in a prompt. Except the body of the response would all have to become part of a prompt.
But the whole dataset it has access to doesn’t have to be mentioned in the conversation, so doesn’t have to be part of the prompt. Ultimately you don’t want your AI assistant telling you everything it knows in each interaction, just to access some slice of your data world, make changes to it, then eventually get you an answer or a report.
What is FreeGPT by the way?
I’ll try to get the actual name and repo since i want to leverage it. It’s basically a reverse engineered chatgpt that is open source.
But yeah, i think the idea is you have prompts trigger the API call to get the additional data.
I didn’t, but I also wasn’t sneaky enough.
My sister had a marketing gig that she got let go of, because she was so good at selling her product that the company said they established strong markets in her area and didn’t need the publicity anymore.
Exactly that: too good at her job.