Really like the idea of having a single place that shows me the throughline of work across different platforms
HN user
milst
milstead@tambo.co
The Library of Babel contains every possible page of 3200 characters that could ever be written. Every book, every sentence, every truth and every lie, all already exist somewhere in the library. Your life story is somewhere in there.
You can search for occurrences of specific strings, which I did to find this page (ctrl+f "hackernews"): https://libraryofbabel.info/bookmark.cgi?omrcw_befyz107
by @chiefofautism on twitter
It's that plus the hosted service which interacts with the LLM, stores threads, handles auth, gives observability of interactions in your app, etc.
With this you build your own React components and register them with the AI. The AI chooses which to use and what props to pass into them, so it's not generating UI from scratch, if that's what you mean - other Michael from the Tambo team
Interesting, reminds me a little of another project posted here a few weeks ago: https://news.ycombinator.com/item?id=45823938
under the hood messages are sent to Tambo which knows how to use the timeline component (sort of like an LLM tool) and can fill the component's props with whatever data it decides. The actual data at this point is completely generated by the LLM (which seems to be ok for historical data on popular topics.) I should add a tool to allow tambo to fetch data from wikipedia before trying to generate timeline data.
Comparing timelines is an awesome idea, understanding when certain events happened in relation to others is really interesting. Maybe even overlaid in different colors or something instead of separate timelines.
Here's the repo btw: https://github.com/MichaelMilstead/timeline-of-everything
Very interested in the idea of an AI being able to interact with my filesystem.
we experimented with something like this: https://local-note-taker.vercel.app/chat
repo in case you'd rather run it locally: https://github.com/tambo-ai/local-note-taker
Curious to compare how our two ideas are built differently, feel free to reach out (email in my profile)
started something like this, but without the "zoom" https://timeline-of-everything.milst.dev/
very cool. Made something with a similar idea, but using timelines instead of maps. I wonder if the two could be combined in some way https://timeline-of-everything.milst.dev/
Very cool. Are the posts I see random from all stored, or are they the latest posts or something?
This is awesome. I worked on a 'conversational historical timeline generator' a little bit ago: https://timeline-of-everything.milst.dev/
I wonder if something similar could be added here where I say something like "what's the most important descendant of x" and it would bring me to that tech and give me a little explanation of why
updated the 'overview' generation
True, and it says that almost every time... I'll do some prompting to stop that
thanks! Any ideas on how to get around overlapping titles? Was thinking maybe truncate with ellipses like "Some long titl..." but often there are too many events too close together for that to make a difference
What’s a good way to learn to understand concepts in a spaced-repetition way? I’ve used anki before for remembering facts or answers to specific questions, but is there a standard way to setup spaced repetition flashcards to learn, for example, when to apply a certain software pattern or something?