Vineet Dixit

@eastdakota @Cloudflare Is there Bentonville CF office?

Sitting at a bar in Bentonville, Arkansas sending offers to new @Cloudflare employees. So incredible and inspiring to read all their backgrounds. #thefuture

@felixrieseberg @vite_js @tan_stack Is this a good old SPA?

A small ship I love: We made Claude.ai and our desktop apps meaningful faster this week. We moved our architecture from SSR to a static @vite_js & @tan_stack router setup that we can serve straight from workers at the edge. Time to first byte is down 65% at p75, prompts show up 50% sooner, navigation is snappier. We're not done (not even close!) but we care and we'll keep chipping away. Aiming to make Claude a little better every day.

@mattpocockuk @Stevie_658jjh How do you clear the context window?

@Stevie_658jjh Debugging a slow React Router loader. 200K was trying random stuff and getting confused. Cleared the context, and it solved it.

Doing some experiments today with Opus 4.6's 1M context window. Trying to push coding sessions deep into what I would consider the 'dumb zone' of SOTA models: >100K tokens. The drop-off in quality is really noticeable. Dumber decisions, worse code, worse instruction-following. Don't treat 1M context window any differently. It's still 100K of smart, and 900K of dumb.

@andrewchen I read every single line of code AI generates before accepting it. But I don’t use agentic code generation. Only autocomplete in Cursor or chat interface in Gemini or Claude.

One question I've been asking founders is: do you try to review all the code that the LLMs write or do you just accept it? I think it's about 50-50 right now but the momentum is towards just accepting the AI-generated code and I think that number will eventually go to 100% This is one of the most telling indications of how AI-native a team is. It's hard to get super high throughput if you are reviewing every line Poll: what do you do?

@GergelyOrosz Those times were different. I’m quite certain that most companies will figure of building, running and maintaining custom tools in the near future.

Cannot wait for teams that build their custom JIRA/Workday replacement/custom CRM to one day turn around and ask: “Why do we have so much internal software that is buggy / has poor UX + we need to maitain?” Seen this movie well before AI, when Uber built uChat (custom Slack)

@samlambert @threepointone hahaha. This interaction is straight gold

@threepointone Mein aa raha hoon papa ji

do you ever crave a jacket potato?

Some heroes wear capes — Chief Aaron Edwards wears blue.

@james406 This is remarkable. I had the same thought and I was independently chatting with AI and it proposed the same solution. In order to create a buzz around this idea I asked it come up with a new word that acts both as a noun and a verb. It said “ferry”. I love it tbh.

i just used AI to identify a $100+ million opportunity for Seattle. currently, to get across the water, you have to drive all the way around it, as cars don't float this is extremely inefficient. but if you look closely, bainbridge island and seattle aren't actually all that far apart. and if we were to construct some sort of boat that carried cars, it could make the trip much quicker together with claude code, i planned out this potential route for the boat does anyone have any contacts in the local government?

@howie_hua 4x25x4=400

It's Mental Math Monday with sixth grade teacher Camden from North Dakota. How would you mentally calculate 25×16?

@Aiblemitx @AnthropicAI at least for last 25 minutes. tried twice. still down.

Is Claude down for anyone else right now? @AnthropicAI “temporary service disruption” message and wasn’t sure if it’s just on my end. AI folks, let me know 👇 #Anthropic #Claude #ai #viral

@tannerlinsley @fishcake2026 Why Solid 2.0?

I also used Remix 1 and 2 for a long time. It was great! TanStack.com ran on it for a good long while. TanStack Start is where that journey eventually took me though (I missed TanStack Router for full-stack, better type-safety, client-first APIs, etc). I'm curious to see where Remix 3 goes, too, however it still feels early, it's a big ecosystem departure from React, which isn't perfect, but really great still and even if/when it's ready, from what I've seen, I'd probably switch to Solid 2.0 before considering Remix 3.

I am so torn now. Remix 3 or TanStack. One is familiar, one is super promising. Why the world has to be so cruel 😢

@steveruizok Da Vinci of our times

I should post these more

noticing that the "I kept beautiful notebooks" people are thriving in claude era

@karrisaarinen @linear Lurker 😆

1) what @linear

@ryanflorence Good man! 👍

I'm not too thrilled how Cursor is becoming unusable because it can't decide to between Agentic first vs Chat/completion first. I can't just ask a simple question in chat without it performing complex gymnastics in the background. All I wanted to ask was a syntax of a standard API.

Supabase down? (Not a user. Just here to get free Planetscale credits)

Remote work forces a written culture. A written culture means the AI can engage with your culture and act on it.