Founder @slashspaceai (previously RabbitHoles). A canvas-first AI tool for high performers▫️ dropped out cs @ucriverside.
In my head
Joined June 2014
- Tweets7K
- Following1.3K
- Followers1.7K
- Likes65.4K
Pinned Tweet
Introducing Slashspace✨
A canvas first agentic harness for power AI users. We are trying to replace all UIs with one interface for the AI era.
For the past 18 months i've been building this and it's finally taking shape towards being the ultimate AI interface for a power AI user.
We iterated on the canvas experience many times. Started as RabbitHoles AI with node based conversations. Slashspace is now evolving towards canvas-as-context app - The nodes are all agentic, and you don't need to draw connections and do the manual work.
Today we're launching on @ProductHunt, and your support will mean a lot! As a solo bootstrapped founder, I've invested a lot into this product, so please show some love!
👀 Some feature highlights
• Canvas with multi model, multi modal chats.
• Local storage with all canvases stored in your folder system
• Agentic nodes that can see all the context on the canvas.
• Connect to @cursor_ai sdk and use the cursor's harness locally, but chat on the canvas
• Access to all the @composio supported tools on the canvas.
s/o @thisiskp_ for hunting our PH launch.
s/o to @tibo_maker, @tdinh_me, @dayonefoundry &
@HackerResidency gang for forcing the clarity out of me on repositioning the product
A good enough ASI will arrive at the same conclusions as the universe it exists in. In ours, love is the conclusive answer.
It doesn’t matter if we run a trillion dollar gpu cluster, spend a decade meditating on a mountain, or drop a $10 psychedelic, we’ll arrive at the same conclusions as long as we’re in this universe.
exactly this is an interface problem. having AI interfaces that are designed to weigh against multiple possibilities is important.
as a founder, and as a designer, glad to see my hypothesis looking back me from other people.
this is core reason I’m continuing to bet on slashspace.ai
this is very clearly an interface and interaction design problem, not something inherent to agents. the system is designed in a way that encourages maximal decision deference to the machine, under the guise of machine intelligence. it is also designed in a way that encourages passive, disengaged interaction with the system.
anyone even remotely familiar with decision architecture and the decision support v automation distinction can instantly recognize that the way information is structured and presented, and the role the user is placed in within the user-machine interaction dynamic is one where the design intent is for the system to make the decision (as many as possible!), and the intended role of the user is to approve it -- ideally approving as few decisions as possible. this drives engagement in a facebook-y social media way, but leads to vastly worse outcomes.
the results are evident.
also -- while (obviously) I'm a big proponent of thinking deeply about how we rearchitect organizations and thoughtfully design work, I do think this particular issue is a design problem *first*, and an organizational architecture problem *only* insofar as organizations are forced to behave defensively against adversarial product design as long as better alternatives are not available.
interesting, but nothing new!
algorithmic feeds have already exposed this phenomenon at scale. humans are mostly unaware of how the information feed is influencing their decisions but they’re pretty convinced that it’s their own belief.
taking credit aside, how is this concerning? the expert are deferring judgment but are for sure acting with subconscious training of right of wrong that’s not exposed to the AI.
The cognitive dissonance of AI doomers:
If the universe is a simulation, and the man made super intelligence can also run simulations at the same fidelity of reality, such an ASI will also arrive at the same conclusions as the universe it exists inside of.
Love is the answer. Which will also include love for humanity.
Love this!
“I think epistemic literacy - how to distinguish information from knowledge - is the single most important skill we should be teaching”
Unfortunately the average of Silicon Valley, and the political class is not epistemically literate.
This is honestly shocking.
Three months ago, Hong Wang was awarded the Fields Medal for resolving the Kakeya conjecture in three dimensions.
Today, OpenAI released a proposed proof of the conjecture in ALL dimensions.
And that’s not all. It also announced a proposed existence proof for quantum chromodynamics and a proposed refutation of the Exponential Time Hypothesis.
Experts say that, if confirmed, these would be Nobel prize and Turing award level discoveries respectively.
A journalist just asked me: “What remains for humans to do?”
I think it’s becoming increasingly clear that more and more problem solving will be automated.
But humans will remain crucial in determining the direction of discovery. Deciding which problems are worth solving.
Because the value of a discovery depends on our needs, our priorities and the kind of world we want to build.
There will be a shift from problem solving to problem setting.
I also think there will be huge individual differences.
People with strong critical thinking skills, creativity and imagination will be supercharged by AI.
People without those skills risk surrendering to it.
I’m particularly concerned for children, who may never develop these skills.
I think epistemic literacy - how to distinguish information from knowledge - is the single most important skill we should be teaching.
This post doing so well is a revelation to me! I’ve been blind to assume that everyone is an inherent researcher and that they already do these things .
Probably one of the reasons I struggle to explain the value of @slashspaceai.
found something to stroke my ego, but this does increase the difficulty level of the game. especially if you’re bootstrapped.
What is a philosopher-builder?
A philosopher-builder is someone who starts from a thesis about human flourishing.
Rather than simply looking for a gap in the market, they start out with a vision of the human capacities that are worth developing, what constrains them, and how we can expand them.
They reason from first principles about human potential and translate those insights into products or institutions.
To understand what a philosopher-builder is, it’s important to grasp what they are not:
1. They are not philosopher-kings. They do not have a blueprint for a society or a theory about how everyone out to live. Some of our most importance capacities are independent judgment, creativity, and the pursuit of knowledge. They seek to expand these capabilities, not prescribe outcomes
2. Open to disconfirming evidence. A strong philosophical starting point is open to rational criticism and has to be tested against reality. Their hypothesis is open to challenge and evidence should not only inform how they build their product, but potentially cause them to revise their underlying thesis. Philosophical seriousness demands intellectual humility.
3. Not a nihilistic iterator. “Make something people want” is a powerful entrepreneurial discipline, but by itself, it cannot establish whether satisfying people’s immediate wants advances human flourishing. You cannot outsource your belief in which ends are worth pursuing to market feedback.
The philosopher-builder is someone who combines philosophical conviction with empirical discipline. They have a vision, ambition, and an openness to revision.
We believe that AI isn’t a normal technology like the internet or the smartphone that society will simply absorb. Instead, it will create the biggest opening for institution-building since the American founding and philosopher-builders will be more important than ever.
If this vision of how to build resonates with you, we want to hear from you.
this proves the core hypothesis I have for @slashspaceai. linear chats are brainrot machines. they’re straitjackets that don’t let the brain flex much.
all the mainstream harnesses are built to involve less as less of the human brain as possible.
🔥Just launched Slashspace v4.1
Popup Chats
When we're exploring a topic, we have a lot of quick questions that don't need to be a branch. Until now, branches were the only way. This update introduces Quick popup chat that let's you ask a question without committing it to a node on the canvas.
Other updates
We can now reference other nodes in the text node, stick the node view panel to either side of the window. Performance improvements, bug fixes, and a 50% reduced app size.
Full blog post is here: slashspace.ai/blog/slashspac…
I was at a cafe yesterday, and overheard a 20 something looking dude enthusiastically talk about how he codes better in C than C++ and that python is an easy language to learn. His friend / colleague was also agreeing with him. This was in the middle of a tech center in India.
The world is too big and X is a bubble.
I’ve replaced screen studio with Claude. This demo video is entirely created with Opus under 30mins while I was afk
Slashspace 4.0 is out 🎉
Press **Option+/** in any app, ask your question, and the answer lands on your canvas. Here's what shipped:
⌥ Quick Window (Mac)
Ask a question or paste a note from any app without opening a canvas. Questions become chat nodes and notes become text nodes, in your last open canvas or any canvas you pick.
*Why:* opening a canvas for every quick question is friction. Now it's one shortcut, and nothing you jot gets lost. We want Slashspace to be the tool you reach for every day.
🗂️ Stacks
Select two or more nodes and choose **Stack** to fold them into one deck. Click it to spread them out, drag one out to unstack it. A stack still passes all its members to a chat as context.
*Why:* big canvases get crowded. Stacks free up space so you see only what you're working on, and stacked nodes aren't drawn on the canvas, so it stays fast as your projects grow.
▶️ Replays (beta)
Click **Share** to publish a canvas as a link anyone can watch build itself, step by step. Hide dead ends, fold long messages, choose whether your name shows, unpublish anytime.
*Why:* a finished canvas shows where you ended up, not how you got there. We're testing whether sharing that journey with your team or audience is useful. It's experimental, so tell us what you think!
Also: text nodes are now pages with / commands and to-dos, a new bar for multi-select, and Image mode on Claude Code, Codex and Cursor.
Full post: slashspace.ai/blog/slashspac…
If you can read and write English, you can learn anything. from basic laws of physics to the secrets of the universe. from how to operate a screw driver to building an intergalactic ship, you can learn anything. the only bottle neck is the noise inside your head that fogs curiosity.
especially true now with AI.
Slashspace 4.0 is out 🎉
Press **Option+/** in any app, ask your question, and the answer lands on your canvas. Here's what shipped:
⌥ Quick Window (Mac)
Ask a question or paste a note from any app without opening a canvas. Questions become chat nodes and notes become text nodes, in your last open canvas or any canvas you pick.
*Why:* opening a canvas for every quick question is friction. Now it's one shortcut, and nothing you jot gets lost. We want Slashspace to be the tool you reach for every day.
🗂️ Stacks
Select two or more nodes and choose **Stack** to fold them into one deck. Click it to spread them out, drag one out to unstack it. A stack still passes all its members to a chat as context.
*Why:* big canvases get crowded. Stacks free up space so you see only what you're working on, and stacked nodes aren't drawn on the canvas, so it stays fast as your projects grow.
▶️ Replays (beta)
Click **Share** to publish a canvas as a link anyone can watch build itself, step by step. Hide dead ends, fold long messages, choose whether your name shows, unpublish anytime.
*Why:* a finished canvas shows where you ended up, not how you got there. We're testing whether sharing that journey with your team or audience is useful. It's experimental, so tell us what you think!
Also: text nodes are now pages with / commands and to-dos, a new bar for multi-select, and Image mode on Claude Code, Codex and Cursor.
Full post: slashspace.ai/blog/slashspac…
I agree with the sentiment, but also I think orchestrating and managing things at a scale also gives us friction and it's not easy to do.
As you invite more agents to our work, and create software factories to be more productive than ever, you’ll soon outsource everything to an agent, even the thinking.
The work you will do will feel frictionless, it will feel amazing on the surface, but once you go a bit deeper, it’ll feel extremely shallow. It won’t reflect the struggles you went through, your decisions, and ideas.
It will no longer remind you of you and the work you aspire to.
You will turn into just another extremely efficient producer of things, but not a creator like you were before.
Invite friction to your work.
It’s a classic engineer’s blindness to think that everything is utilitarian, and that everyone’s internal world is oriented towards identifying problems and chasing solutions.
I’ve seen this from a lot of engineers ranging from Elon to Pieter here. I respect them a lot in business and engineering, but I don’t think they’ve spent time talking and understanding other humans with enough depth.
Such takes are completely ignoring the quirks of the human mind.
1. Not every has the same IQ. And if someone’s IQ is below 100, their ability to communicate solution clearly declines exponentially for every 10 points. That directly translates into the capability to prompt as well. It’s sad, but most people don’t even have a cohesive dialogue in their heads.
2. Not everyone has good taste. Most of the times we prefer to buy things from people who are more tasteful than us. Almost everyone has a high quality camera with them, but that doesn’t mean we stop enjoying or paying for professionally made cinemas and photo shoots.
3. Not everyone enjoys problem solving like engineers do. We can see these examples everywhere in life. A majority of the people don’t attribute the same axiomatic importance to solving problems. It’s a very engineer/entrepreneur thing.
4. Not everyone has a thirst for knowledge like nerds do. Maybe the average person can prompt a jet into existence based on what they already know like luxurious, travels faster than sound, references design to something that already exists. But to create something like a B2 they will require first principles thinking about physics, and persistent motivation towards a vision, and thirst to enjoy science.
5. Not everyone thinks and operates like us. If you spend enough time trying to understand the internal world model of someone else, it’ll humble us to realize how vastly different our internal models are compared to other humans. It’s a miracle that we found language, and common logic to live in harmony, but we’re way more different than we’re alike. This also means creativity is boundless.
6. Thermodynamic efficiency. As a collective species, if everyone always builds things from scratch ingredients we’d be wasting a lot of energy. It’s more efficient to make use of solved things. If some agent, or someone has already built something useful, tested it, and is live, asking another agent spend energy doing it from scratch makes make thermodynamic sense.
7. Lack of epistemic humility. Most people who claim “something is forever solved” lack epistemic humility. People on the edges of creating new human knowledge often get very humbled realizing that despite knowing sooo much, we still have infinitely soo much more to solve. I’m not talking about phd levels, I’m talking about scientists and inventors who go so deep that they end up becoming philosophers.
AI is like a universal fabrication machine. Having a fabrication machine doesn’t mean we’ve exhausted every possible thing to fabricate or that everyone is going to fabricate everything all that time.
Sure the old era of software for simple utilitarian cases are dead, but we’re only evolving. We can’t close the book cause we commoditized wheels, we proceed to invent turbochargers, hybrid engines, turbojets, f1 engines, and so on.
