This is super useful! Have you considered generating docs based on customer support in Slack or Discord conversations?

Yes, Promptless already has the ability to be triggered from Slack channels (e.g. Slack Connect support channels with customers). Discord likely coming later this week or early next week!

Happy to get you set up on either!

@Obscurity4340 Interested in bouncing off ideas for therapy? Email is in my about box :)

Can you give me a little hint about it? Not that I wouldn't be happy to chat, just preliminarily curious before I reach out :)

@yonom Whatever you feel comfortably publicly sharing and then if I feel like I have anything of value in turn, I'll reach out privately :)

(taking care to avoid doxxing myself)

Yes, obviously! I began a blog post on the issues with Trusted Computing but ended up first writing up on the way Trusted Computing works, since most explanations I could find would bury the underlying motivations behind technical jargon.

It is an excellent explanation. Great job!

This is cool! Are you using one-shot learning under the hood with a user provided example?

BTW: Here's a more performant version (fewer tokens) https://preview.promptjoy.com/apis/jNqCA2 that uses a smaller example but will still generate pretty good results.

This is still pretty fast - impressive! Are there any tricks you're doing to speed things up?

Thanks. We find few-shot learning to be more effective overall. So we are generating additional examples from the provided example.

- if the only reason you're using v4 over v3.5 is to generate JSON, you can now use this API and downgrade for faster and cheaper API calls. - malicious user input may break your json (by asking GPT to include comments around the JSON, as another user suggested); this may or may not be an issue (e. g. if one user can influence other users' experience)

I would recommend creating a simplified JSON schema for the slides (say, presentation is an array of slides, each slide has a title, body, optional image, optional diagram, each diagram is one of pie, table, ... Then use a library to generate the pptx file from the content generated.

Library? What library?

It seems to me that a Transformer should excel at Transforming, say, text into pptx or pdf or HTML with CSS etc.

Why don't they train it on that? So I don't have to sit there with manually written libraries. It can easily transform HTML to XML or text bullet points so why not the other formats?

I don't think the name "Transformer" is meant in the sense of "transforming between file formats".

My intuition is that LLMs tend to be good at things human brains are good at (e.g. reasoning), and bad at things human brains are bad at (e.g. math, writing pptx binary files from scratch, ...).

Eventually, we might get LLMs that can open PowerPoint and quickly design the whole presentation using a virtual mouse and keyboard but we're not there yet.

It’s just XML They can produce HTML and transform python into php etc.

So why not? It’s easy for them no?

I believe functions do count in some way toward the token usage; but it seems to be in a more efficient way than pasting raw JSON schemas into the prompt. Nevertheless, the token usage seems to be far lower than previous alternatives, which is awesome!