Machine Learning

1 readers

1 users here now

Community Rules:

Be nice. No offensive behavior, insults or attacks: we encourage a diverse community in which members feel safe and have a voice.
Make your post clear and comprehensive: posts that lack insight or effort will be removed. (ex: questions which are easily googled)
Beginner or career related questions go elsewhere. This community is focused in discussion of research and new projects that advance the state-of-the-art.
Limit self-promotion. Comments and posts should be first and foremost about topics of interest to ML observers and practitioners. Limited self-promotion is tolerated, but the sub is not here as merely a source for free advertisement. Such posts will be removed at the discretion of the mods.

founded 1 year ago

MODERATORS

communick@academy.garden

[D] How are Tome.ai and these other LLM powered presentation builders working under the hood? (alien.top)

submitted 11 months ago by Alert_Invite_9205@alien.top to c/machinelearning@academy.garden

2 comments fedilink hide all child comments

I would assume they just have some prompt they are handing to GPT4 (or some other model), with instructions to build it into a deck outline. But how is that deck outline produced by the LLM then getting translated into visuals in powerpoint?

you are viewing a single comment's thread
view the rest of the comments

[–] Rejg@alien.top 1 points 11 months ago

It seems like it would be split into two layers; the LLM would first plan the presentation based on the user provided prompt and bind it to some kind of template (IE: Title Slide, Big Number, etc) outputting a JSON. Then, take each template and run another LLM call and outputting the details of each slide as another JSON while concurrently running calls to an image creator or image search to fill in the template.