Video yükleniyor...
Video Yüklenemedi
I've been frustrated with the linear chat experience for learning, so I used Fable to help rethink it. Introducing Rabbithole 🐇, an infinite canvas where you can select anything, ask anything, and your questions branch instead of stack. This lets you pull on a thread until your curiosity is... show more
88,986 görüntüleme • 4 ay önce •via X (Twitter)
41 Yorum
Ask Claude Code/Codex to set it up for you:
this is so cool. feel like this should be the ideal "chat" interface
yes! each comment will an agent next
nice work! I had similar pain points but chose to hide threads when i'm resolved with it. i want more and more people to try out new interfaces!
Cool! You can minimise threads in rabbithole!
I explored something similar but where it breaks really quickly is the mental model in your head. It’s like having a dozen conversations at the same time. It’s impossible to keep track of it. I kind of thought of a different approach recently. Instead of retaining all the conversations and just branching constantly it actually follows you to the direction you want and discards the rest. This is in fact how conversations work. How many times have you talked to a friend for two hours only to find out at the end that you covered like dozen different topics? I think humans are better wired for this. Something like this.
Working on something similar - a spatial pdf reader for the @daylightco tablet A canvas is a much better interface than chat for learning
@daylightco Does Daylight have a mic? Voice would seem to be a more intuitive input modal
@daylightco Love that idea, adding it now
@daylightco @shloked added it, let me know if you have any other ideas
Cool, feels like a lightweight version of heptabase. First test worked really well, thanks for sharing!
didn't know about heptabase! thanks for sharing
I love these kinds of projects, but I'm confused. The UI is monotone, the only thing that helps to see which idea where is a super thin line. No colors. The tutorial names the problem: conversations are linear. The examples you show are linear. The only example of interconnected nodes come from very simple questions you highlighted and are not organized. 0:31 shows some questions from the top left branching to the bottom right below other cards. Did it really completely change the way you learn with AI? Maybe, but there are still decisions that carry cognitive tax.
This looks INCREDIBLE!! I've been waiting for something like that!
this is exactly how my brain looks when i learn things
dude this is sick and such a great idea!!!! you don't know how many times i've branched and gone totally blank three prompts later. fuck ya
Amazing! I’ve wanted this for months!
cool project! this reminds me of code bubbles from andy van dam's lab at brown:
Will check it out! Thanks for sharing
lovely! this is from my notes to self from last week. excited to use Rh today
beautiful - as if my ADHD was not enough :P
This is exactly what I have been wanting OpenAI/Anthropic to add into ChatGPT/Claude
wait this might actually fix the "scrolling back for 10 mins to find that one answer" problem
This is the idea that I've had, but using codex side chats were good enough for me. Literally almost similar capability but without breaking cache
Good one
@andy_matuschak looks like something that would interest you.
I've wanted something like this for so long
I can't tell you how many times I've wished this existed.
For god sake I wait for months for a similar feature in ChatGPT web interface, really helpful. Appreciate the work.
Love it! Something I missed but couldn't put my finger on :)
Add a voice agent so I can use it in my car.
This is information stacking, not learning at all. Right @amicusadastra ?
was considering building something like this myself, thank you
great job!
Great work. Very useful :)
finally! im surprised this hasn't been the default the entire time
Great idea. This is a cool way to branch conversations without losing the main thread.
Very nice!
This looks so awesome
Freaking amazing project. Loving it so far.
Nice idea @shloked Definitely will give it a try
![One of the smartest things you can do with Fable 5 right now: Re-create your AI second brain to log all your business ideas, personal context, and important data. The first time I built an AI second brain was with Opus, but I recently re-created it with Fable 5, and it blew my mind. Here's exactly how to get started: Step 1. Set up your Obsidian vault Download Obsidian from Obsidian dot md if you haven't already. Then, go ahead and create a clean vault with your most important folders. For example: /ideas → business ideas, content angles, random thoughts /context → who you are, your business, your goals, your stack /data → important numbers, portfolios, metrics /log → daily entries, decisions, lessons learned This is your database. Everything Fable reads lives here. Step 2. Connect Fable 5 to your vault I like this Claude Code prompt: "/goal connect to my Obsidian vault at [path] and act as my second brain orchestrator. Read everything in /context before every session. Log anything new I tell you to /log with today's date." Fable now reads your vault before it answers anything - it knows your business, your goals, your history. Step 3. Build the self-update habit Every time you have an idea, a decision, or a lesson, tell Fable: "Log this to my second brain: [thought]" Step 4. Start querying it You can start sending prompts like: → "What are the most common themes across my last 30 ideas?" → "Based on my context, what should I be prioritising this week?" → "What decisions have I made about my content strategy so far?" Opus was good at this, but Fable is on another level. I feel the depth of reasoning it brings to your data is genuinely unlike anything I've used before. Some might argue it's a bit of overkill to use Fable for a simple second-brain setup, but if you have the means, it's 100% worth it. Build this once, and it'll compound forever.](https://image.24vids.com/tw-2076900303748895011/amplify_video_thumb/2076900248182779904/img/kjGVB6hRJW-pVScS.jpg)
