It's not super serious, but it's not meant to be -- it's not pitching to be your enterprise AI strategy. However, even though it's presented in a playful way, I suspect it's quite powerful, and expect The Internets will build some cool stuff atop it.

It's a fun and creative way to explore playing with LLM's, and it's brilliantly executed! Happy to see it here on HN.

This seems like it could be really powerful and actually useful.

I just spent the last few hours typing in the specification of a Freshman programming project that I use to teach, Rock, Paper, Scissors.

Specifying the programming assignment using either Python, C or C++, using their parameterization feature. Parameterization is very cool by the way!

It would routinely miss putting any headers in for the C or C++ examples. Once in awhile it would generate actual working code in C and C++. But it was all unindented. The same for Python also. The Python code had no indenting everytime causing indentation errors for the Python environment. I tried many different ways of specifying indentation for the text output; it didn't work. Possibly b/c of the HTML output being generated. It's 90% there, but the user would actually have to have some knowledge of the programming language to make sense of the errors.

The UI built by Tldraw is different from a chat interface. That doesn’t mean it’s not a good fit to interact with an AI/LLM.

I definitely see this in the hands of kids, just like they are great interfaces to code video games without writing a line of code.

Interesting product and obviously awesome execution, as expected from tldraw… but yeah… seems like a very strange departure from what Steve has been building the past few years.

The core product / pitch is still the same—an SDK for whiteboards and other infinite canvas stuff—and that's what we monetize through licenses. Computer (and our other demos) are basically marketing, R&D, and fun.

Well if you're looking for fun stuff... could you make a tool that lets me easily breadboard [1] an app, and then you GenAI it into a low-fidelity clickable prototype?

As always, excellent execution on this, Steve!

[1]: https://basecamp.com/shapeup/1.3-chapter-04#breadboarding

> really novel UI for LLMs

Are you referring to Tldraw Computer or something else? Don't get me wrong, it looks really nice but not that different from other graph representations of LLM workflows, including live updates in the nodes themselves.

It reminds me of a tool I saw recently called Heuristica [0]. Would like to try it but I don't like being tied to a subscription and the free plan seems quite limited if I can't even plug my own key in. Don't see why this can't do what Heuristica does! :)

[0] https://www.heuristi.ca/

At one point, I also worked on making it work with a personal API key. However, this added a lot of complexity. It felt like I was building and maintaining two separate branches of the same app, so I had to put the idea on hold. I might revisit it in the future.

I totally get it though, it's a difficult thing to balance. If I was doing lit review and deep research daily 6.99 is an amazing deal.

https://github.com/excalidraw/excalidraw

https://tldraw.dev/ FAQ: Is the tldraw SDK open source? Our license is not exactly Open Source but you can view the source code on GitHub. We accept contributions from the community and work in public.

I also understand the hilarious spin that you added considering tldr (too long didn't read) lmao. but still its worth your email.

Crazy how I realised that tldr meme after I had written the first paragraph

It's an unkind thing to do to your prospective users.

From Bleeping computer's coverage the last time someone tried to dump Relay in with a disposable email blocklist:

> Back in November 2021, Firefox Relay's team lead had requested the maintainer of a separate burner email list, "burner-email-providers" to exempt the particular domain form the blocklist:

> "We are operating Relay with a number of features that I think mitigate the risks that these aliases pose," Mozilla's privacy and security engineer Luke Crouch explained in November.

> Firstly, if a @mozmail.com alias is disabled by the user, any emails sent to the alias are not bounced back but instead discarded with a 404 error message returned by the service's HTTP webook, stated Crouch.

Secondly, he explained, the anti-abuse protections built into Relay limit free users to a total of five aliases, and further rate-limit premium customers so they cannot abuse the service by creating large-scale throw-away aliases for, say, automated signups to web services.

> With that reasoning, mozmail.com was swiftly removed from that blocklist. And it appears, the creators of "disposable-email-domains" have also honored the clause, for now.

To whom exactly are you talking to?

I have been using tldraw with one of my friends or even generally when my whiteboard marker goes down and I wish to draw.

Seriously tldraw makes sharing whiteboards so easier as compared to excalidraw and others.

TLDRAW deserves more attention than excalidraw and I watched its demo video and

holy moly , this is so crazy , the fact that this can create semi websites and etc. feels so cool , definitely going to try it

EDIT: I guess you were talking about tldraw rather than excalidraw.

https://github.com/tldraw/tldraw

I am sorry I guess then for this comment , excalidraw also works great but I still just like tldraw because of how familiar I have become of this interface.

Shame that the licensing of tldraw is less permittive than excalidraw but I guess I am just a little bit okay with it considering its still open source and though I maybe wrong I had read the license , and it seems that it was focusing way more on that you had to have the name of tldraw / packaging of tldraw / copyright

here is the license restrictions

    Not to disable, hide, remove, or alter the Watermark.
    Not to disable, change, or interfere with the license key validation process that governs the display of the Watermark.
    Not to remove any copyright or other notices from the Software.
    Not to make the Software available under a license that supersedes or negates the effect of this License.
    Not to distribute the Software or modifications of the Software as a standalone product, but only as part of another application.
    To include a verbatim copy of this License in any distribution of the Software.
    To comply with tldraw's trademark policy.

They should be extremely proud of the culture they've managed to foster and I genuinely hope to see them succeed as a business.

I've joked before that the last generation of human machine interfaces ware invented at Xerox park, and the next generation is being invented at TLDraw of Finsbury Park. But it's not really a joke, I genuinely believe it.

So this is the demo people were talking about at the end of the night! I was quite annoyed I missed it, makes sense now. I think I was nerding out over current-gen HIDs while eyeing up their very tastefully equipped coffee station (ozone roasters ftw)

I see just an email signup thing, can't figure out if i can slap this onto the ai backends I'm building

Visual programming is a tempting idea I love. It rarely works, but this might be the case.

I think there is a lot of room for AI UIs - between chats (the simplest and most prevalent) and arbitrary code (even if it is "just API calls", it is only people with at least some software inclination).

One thing I am keeping track of is WordWare (https://www.wordware.ai/), which makes it easy to create a sequence of operations. It feels like an "Excel formulas of AI".

Yet, I like the visual, graph-based approach of Tldraw.

Is the magic here making a flow chart / workflow where sample data is generated to make it easier to visualize and you can update and see the results?

We had a bunch of fun putting this together so I'm really happy to see folks enjoying it. I'm not sure where the project is going but I've been waking up for weeks with a fresh "oh christ, we could do ___", so that's exciting.

Ask me anything!

Any chance you’ll make the source available?

There are about 50 extensions I’d make to it if I could! (And I’m sure I’m not alone.)

there's been a rising tide of academic HCI work in a similar space, wonder if there will be cross-pollination of ideas along these lines (many more papers i'm sure but some off the top of my head): https://arxiv.org/abs/2305.11473 https://arxiv.org/abs/2309.09128

I should really share the design doc from when we started putting this together. The core idea here was a) making a little hobby machine on the canvas and b) using LLMs to “power” the widgets. Somehow that ended up looping back to “ai workflows” but definitely not where we started. I’m only catching up on the space now!

It's Yahoo! Pipes for AI.

This seems easy enough if I have a code component that could execute arbitrary code. I could just write a couple small component (take API key, text, post to twitter/search wikinews) and add them to the workflow. If the components I needed were generalizable I could share them on some kind of community repository - so the next person who needed a "Post to twitter" component wouldn't even need to rewrite it.

I'd like to know if I can use the SDK to build workflow/process diagrams that specify inputs, outputs, and side effects (ie, this process creates a pile of logs or documentation) and then export a process specification for use in another application.

My specific use case is process mapping and quality systems implementation in a hardware engineering setting.

At the end of the line these are just function definitions -- a black box that takes well defined inputs and produces well defined outputs, as well as calling out side-effects (I suppose these could just be more outputs).

I'm curious how the internal prompting works in certain cases, and whether there's any way to customize a particular module's default or hidden prompt. Particularly with speech. I was trying to get it to sing a made-up Christmas carol, with generate lyrics and chords. I tried a bunch of different ways, but at best the speech module would only read it out. In one funny case, the speech module added on its own beforehand: "a spoken-word piece".

I made a "Cuisine Synthesizer". [Edit: Updated to "Fusion Food Truck Simulator"]. I love how easy this was to snap together! https://computer.tldraw.com/p/m15giebhYxD6RfWmho7R5J

needs something like a "tool use" or "python script" component to call out and get a proper random choice according to your instructions

I clicked on one of them, which took me to the actual app. When trying to click the button to generate something, it asks me to login/sigup. Fine, I signup. Then once finishing the sign up, I land on some sort of index page with tutorials and "my projects", but not at the demo I first wanted to see.

So I go back to HN, to this submission, click on the link but it still takes me to this index view instead of the blog post/page I first read. I just wanted to see what happened when I clicked the button inside the app...

Second thought: is this meant to work in mobile as well or not really? Tried it on chrome IOS and could not move the tiles around.

The video on their homepage gives a good idea of how it will work: https://www.youtube.com/watch?v=u1016UnJIgA

My only refrain would be that it uses Google's Gemini, a very poor choice of an AI model collection.

But they just seem to be churning out random AI demos?