Building @kritapp • I’m gonna be king of the Pirates

Joined June 2014
255 Photos and videos
Pinned Tweet
Things I believe: We are meant to build. Creation is the purest form of agency. It's how thought earns the right to exist. You don't understand something until you've made something from it. Progress doesn't happen. It’s forced into existence. Nothing improves until someone refuses to accept inertia. The future is an act of defiance against stagnation. Every problem stays unsolved until someone decides it shouldn't be. Technology encodes intent. A tool isn't neutral - it carries a worldview. It makes some forms of work easy, and others invisible. Every tool teaches you what its maker believed was worth making. The right tools don't replace curiosity - they amplify it. Speed is a truth amplifier. Moving fast exposes what actually works. Momentum collapses illusion - you collide with reality before you can rationalize it away. Slow and steady is often just slow and scared. Momentum builds clarity. Energy is a competitive advantage. It's not a personality trait - it's a multiplier. People who move fast and think wide change outcomes. Energy compounds faster than skill. Delusion is underrated. Every breakthrough begins as an unreasonable belief sustained by effort. Rationality optimizes the known - delusion expands it. You have to be slightly out of touch with "what's realistic" to make anything new. Abundance builds better things than fear. Fear creates safety. Abundance creates vision. Work born from fear seeks to protect - work born from abundance seeks to invent. You can't create something bold if you're defending something fragile. Reality rewards iteration, not speculation. You don't learn by guessing - you learn by colliding with the world. The faster you ship, the faster you evolve. Bias toward action beats theoretical perfection. Judgment is the rarest resource. Tools can be built, processes can be cloned - discernment cannot. Good judgment compounds faster than capital. Protect yours - build around people who have it. Ambition is a duty. Playing small doesn't make the world better. To aim higher isn't arrogance - it's responsibility. If you have potential and waste it, you're not being humble; you're being negligent. Most limits are inherited, not real. Reality is negotiable - physics isn't. The boundary between possible and impossible shifts with every act of courage. The only real constraint is the one that holds the universe together - everything else can move. Presence creates possibility. Most breakthroughs don't happen at the desk - they happen in the world. Every new person, every new place expands your mental surface area. You can't collide with luck sitting still.
3
11
1,220
/ahh-shit
As a result of a US government directive, we are suspending access to Claude Fable 5 for all users. You can continue to use all other Claude models. Here’s what this means for you: Across Claude products, new sessions will run on your selected default model or Opus 4.8, and existing Fable 5 sessions will end with an error. On the Claude Platform, requests to Fable 5 will also return an error. Please update your integrations to other Claude models. We know this is a disruption to your workflows; we appreciate your patience and support.
1
53
My boy solving real problems
I got fed up with language barriers, so I'm building my own app that allows seamless live translation. DM me if you want to try beta.
2
3
335
A guardrail enforces properties. A conformity enforcer enforces values. And slop is a choice with no rejected alternative.
2
29
Figma should hire me :) 1. Connect canvas with MCP 2. Decent design taste — day 1 3. HTML and CSS instead of rendering iframe 4. Built in interactivity and animations (no other tool does this) 5. Extremely fast
2
1
8
343
Playing around with motion video as an export
2
5
83
Ohhh this is gonna be so good. Cooking something fresh! - Assign AI a user persona - AI will start usability testing on your designs.
1
3
87
Jaideep Singh retweeted
wrapped up my time at @GigabrainGG this month. got to build something I'm genuinely proud of. learned a ton working alongside @0xchetan . grateful for the ride. best wishes to the team and everything coming next for them. as for me, actively looking for what's next. if you're building something ambitious and need someone who ships fast, let's talk 🫡
8
6
20
1,012
Jaideep Singh retweeted
Your motivation on an idea is the reason you will keep working on it not whether market wants it or not.
1
2
129
Jaideep Singh retweeted
We need to stop talking about product design in absolutes… there are no rules. Everything is made up. Do what makes sense and feels right.
166
387
3,116
253,457
“Figuring out the right product is innovator’s job, not the customer’s job” Can you tell what book I’m reading?
1
46
Claude maxxing in the mountains
1
6
147
Shaders are live! You can now generate beautiful shaders and see them live on canvas.
Steal like an artist! You can now Generate UI from screenshots And yes — i'm working on generating 3D assets too ;)
2
181
Steal like an artist! You can now Generate UI from screenshots And yes — i'm working on generating 3D assets too ;)
Updates: 1. Improving design taste 2. Responsive by default 3. Targeted updates on designs
2
270
Updates: 1. Improving design taste 2. Responsive by default 3. Targeted updates on designs
Figma should hire me :) 1. Connect canvas with MCP 2. Decent design taste — day 1 3. HTML and CSS instead of rendering iframe 4. Built in interactivity and animations (no other tool does this) 5. Extremely fast
181
New way to go down a rabbit hole :)
100% agreed. Just tried a prototype and loving this direction
2
95
100% agreed. Just tried a prototype and loving this direction
My main reaction to this is: schools need to figure out AI right now. Learning will be so much more fun and individualized. Current model is dead ma ln walking. Close to 100% of my “learn new stuff” time is done via AI now and with stuff like this it will explode even more.
5
278
For the @paper X @contra challenge Self Healing Product Workflow: - PostHog analytics via MCP - Diagnoser reads the data and pins a user-job hypothesis on the failing screen - Designer applies targeted change as a variant - Guardrail reviews — brand, scope, memory checks - Approved variant exports to JSX, canvas retagged [SHIPPED] - Run 2: memory kicks in — agents pick a different axis instead of repeating what already worked The canvas isn't the deliverable. It's the operating surface. #paperchallenge #claudecode
7
131
*Rolls sleeves up* alright let's begin
1
66