HackerTrans
TopNewTrendsCommentsPastAskShowJobs

mfester

no profile record

Submissions

All the wrong ways to think about AI customer support

mux.com
3 points·by mfester·vor 12 Monaten·0 comments

A “prompt engineered” solution to process Markdown

markprompt.com
5 points·by mfester·vor 3 Jahren·0 comments

[untitled]

1 points·by mfester·vor 3 Jahren·0 comments

Markprompt: An open-source GPT-4 platform for Markdown/Markdoc/MDX docs

markprompt.com
5 points·by mfester·vor 3 Jahren·0 comments

VSCode-mdx 1.1.0 adds support for IntelliSense

twitter.com
2 points·by mfester·vor 4 Jahren·1 comments

comments

mfester
·vor 3 Jahren·discuss
Interesting. Could you share more about the performance characteristics of EdgeDB + TypeScript vs say Prisma + other DB?
mfester
·vor 3 Jahren·discuss
Embeddings are created using OpenAI's ada model. They are stored in Supabase with the vector extension, which offers a simple way to compute vector similarities. Then the associated sections are added to the prompt context.
mfester
·vor 3 Jahren·discuss
Thanks!
mfester
·vor 3 Jahren·discuss
Yes, we plan to do this in background workers soon so that it can carry the load.
mfester
·vor 3 Jahren·discuss
The way it went is: we built this as part of Motif for the past month, and our users loved it. Many asked for a way to add this feature to their existing sites, so we made a standalone platform that streamlines the process, and open sourced it :)
mfester
·vor 3 Jahren·discuss
Yes, this will come, we had to start somewhere. Would love a PR on this, should be straightforward.
mfester
·vor 3 Jahren·discuss
Handmade, but indeed Tailwind.
mfester
·vor 3 Jahren·discuss
Haven't made a comparison yet but would love to hear about any findings. So far, for the intended use cases, meaning narrative docs with lots of text, images and code, it works really well. We're still breaking up the Markdown into sections and comparing embeddings as this strikes a good balance between performance and cost, but will also plan to let users experiment with other approaches, such as sending entire corpuses of text to GPT-4.
mfester
·vor 4 Jahren·discuss
Not yet. We do support file sync though (https://motif.land/blog/syncing-text-files-using-yjs-and-the...) so you can use your mobile Markdown editor of choice.
mfester
·vor 4 Jahren·discuss
Nice work! Regarding your question on how to handle undoing a command on a shape that doesn't exist anymore, is there a way we could automatically recreate the shape?