Your tweet bookmarks

Kit Langton

@kitlangton

·Follow

👀 Well, that was an overwhelmingly positive response. I got a lot of feedback. People mostly said shockingly kind things. But there were some great feature requests and bug reports as well. So, I just pushed an update. Ahem: - Added some prettier open graph images (see  Show more

Kit Langton

@kitlangton

It is time → effect.institute. 2026, the year of 𝚎𝚏𝚏𝚎𝚌𝚝. I'm extremely proud of how this turned out. There are many chapters to add, but I do hope you enjoy what's there so far. Let me know what you think. 🫡

Watch on X

thisisgrey

@thisisgrey

·Follow

Basement Studio (@basementstudio) have been busy branding and building stories for all major gen AI brands like Cursor, Vercel, and ElevenLabs alongside legends like Dailylight. These guys work hard in all the right places. The great future with the old internet spirit. [Link↓]

Ksenia Kondrashova

@uuuuuulala

·Follow

Sometimes we also wonder how people do things in @paper haha Not quite a tutorial but here is what I did: - grabbed a screenshot from video - asked chatgpt to get me a b/w svg image with frame and dots - saved the pic - opened the Heatmap shader on app.paper.design - Show more

Brett

@BrettFromDJ

Built in Figma, animated in Paper in 2 seconds.

Watch on X

ryan vogel

@ryanvogel

·Follow

I am creating a personal finance app because all of the other ones suck 1. uses plaid for my amex transactions 2. will use a poke style personal assistant to ask me what each purchase was for if it can't figure it out and to identify me of trends that I am spending I will make Show more

Rayane

@RayaneRachid_

·Follow

Mon 2eme tool indispensable dans mon setup Claude Code c'est Gemini Design MCP 🔥 Le principe est simple, tu délègues TOUT le frontend et le design a Gemini pendant que ton agent principal gère la logique, la database, le backend. Que ce soit Claude Code, Codex ou Cursor ca  Show more

Qwen

@Alibaba_Qwen

·Follow

🚀 Introducing Qwen3-VL-Embedding and Qwen3-VL-Reranker – advancing the state of the art in multimodal retrieval and cross-modal understanding! ✨ Highlights: ✅ Built upon the robust Qwen3-VL foundation model ✅ Processes text, images, screenshots, videos, and mixed modality  Show more

Cerebras

@cerebras

·Follow

GLM-4.7 from @Zai_org is live on Cerebras! - Frontier intelligence for coding, tool-driven agents, and multi-turn reasoning - Record coding speed: ~1,000 tokens per second (up to 1,700 TPS for other uses) - Strong price-performance: ~10x higher than Sonnet 4.5

Nick Pattison

@thenickpattison

·Follow

When the brief is "Hitchhiker's Guide to the Galaxy meets Vercel-level craft"

Aiden Bai

@aidenybai

·Follow

this is genuinely an incredible piece of work

Kit Langton

@kitlangton

It is time → effect.institute. 2026, the year of 𝚎𝚏𝚏𝚎𝚌𝚝. I'm extremely proud of how this turned out. There are many chapters to add, but I do hope you enjoy what's there so far. Let me know what you think. 🫡

Watch on X

The Bugged Dev

@thebuggeddev

·Follow

Couldn't stop myself from building a website after seeing @kyleanthony's latest Utilitarian style design. I quickly prototyped the hero section in about 30 minutes, then iterated on it to create an almost-finished site using @GeminiApp :D Live: atlas-olive-sigma.vercel.app

Jose

@ragojose

·Follow

recent sites by basement: untillabs.com worldlabs.ai base.org factory.ai rox.com speakeasy.com xmcp.dev

Reggie James

@HipCityReg

·Follow

currently building a "situation monitor" dashboard for the boys

Context7

@Context7AI

·Follow

We fixed Context7 biggest problem: Context bloat. Introducing the new Context7 🎉 ◆ 65% less tokens per query ◆ 38% faster queries ◆ Better output quality

Max Leiter

@maxleiter

·Follow

I wrote a bit about how we made v0 an effective coding agent - Dynamic system prompt - Our "LLM Suspense" framework for modifying streamed content on the fly - Our AutoFixer system for fixing various issues we've seen. A good example of how powerful the pipeline is is our Show more

Zaid

@zaidmukaddam

·Follow

Alam (علام) is now live! → alam.sh

Zaid

@zaidmukaddam

x.com/i/article/2008…

Pontus Abrahamsson — oss/acc

@pontusab

·Follow

Customer enrichment agent: 3 Gemini Flash calls, parallel tool execution, Google Search grounding. ~$0.01 per customer. Stupid cheap.

Chris Tate

@ctatedev

·Follow

You can now opensrc <everything>

Chris Tate

@ctatedev

New CLI just dropped 𝚗𝚙𝚡 𝚘𝚙𝚎𝚗𝚜𝚛𝚌 <𝚙𝚊𝚌𝚔𝚊𝚐𝚎> My workaround for agents struggling with dependencies: just give them the source code. Way better than types alone. They get real examples, docs, edge cases. Been doing this manually for months. Finally automated it.

ryan vogel

@ryanvogel

·Follow

We 100% live in the future with AI, and that future is not with MCP, but agents building their own tools to use It's crazy how well it works, just like hands free

Philipp Schmid

@_philschmid

·Follow

Learn how to unlock structured, repeatable image generation with Nano Banana Pro's and JSON prompting capabilities. 🍌 - Define specific details like lighting to strictly avoid standard model defaults. - Generate detailed JSON templates from reference images using Gemini 3 Pro.  Show more

Guillaume Champeau

@gchampeau

·Follow

Et ce n’est pas une erreur de traduction ni un lapsus

Documentaire et Vérité

@DocuVerite

À archiver: "Les puces d'IA américaines permettront d'alimenter nos giga-usines d'IA et aideront les États-Unis à maintenir leur avance technologique..."

Watch on X

Tanner Linsley

@tannerlinsley

·Follow

Introducing TanStack CAD! ... just kidding. But seriously this is jaw-droppingly awesome usage of so much tech. @SamWillis just raised the bar into outer space with this "demo".

Sam Willis

@samwillis

New demo: collaborative AI CAD in the browser 🚀 Built with @ElectricSQL + Durable Streams + @tan_stack DB+AI+Start - ElectricSQL + DB: data sync - Durable Streams: presence + AI + CAD (Yjs!) sync - TanStack AI: AI for cad modelling 🤯 - Coded with @cursor_ai

Watch on X

Zaid

@zaidmukaddam

·Follow

should i make this live?

Zaid

@zaidmukaddam

x.com/i/article/2008…

Michael Beer

@michaelbeer01

·Follow

I built a Kalshi trading bot to predict formula one races

Dedalus Labs

@dedaluslabs

·Follow

We made every single AI model free on Dedalus until January 12. Use top models from: OpenAI Anthropic Gemini xAI (Grok) DeepSeek Mistral Llama models Show more