Triceps

@damienghader template wears prompt costume now, ok 😏

My prompt: "Build a product landing page for AURA, a premium earbud brand. React, Tailwind CSS, Framer Motion for all animations, Lenis for smooth scroll. AURA is precision engineered silence, design the page like the product deserves to be in a museum. Every section should feel considered, nothing decorative for decoration's sake. Visual language: Near-black surfaces (#0a0a0a base), single warm amber accent light as the only color. Floating product centered in negative space, lit dramatically with soft depth-of-field blur around it. Editorial type hierarchy, oversized display headlines (120px+) paired with razor-thin 11px labels. No gradients, no noise, no texture. Just light, shadow, and space. Motion: Scroll-driven product rotation with Framer Motion spring physics. Section reveals that feel like a curtain lifting, not a fade-in. Micro-interactions on every clickable element, subtle scale, not bounce. Parallax depth on the product as you scroll past it. Lenis for smooth momentum scroll throughout. Sections: Full-bleed hero, product floating in darkness, single headline, nothing else → engineering told through numbers (driver size, frequency range, noise cancellation depth, animated counters on scroll) → materials section where the product rotates to show each surface → colorways with instant background reaction on hover → a CTA section that feels like a reveal, not a form. References: Bang & Olufsen, Apple product pages, Teenage Engineering, Dior fragrance campaign visuals. Fully responsive. Awwwards-level quality, this should feel like Sony hired a luxury creative agency. Every motion intentional, every pixel deliberate."

Lovable is now a better designer than me. Here's everything I know, and how to generate results like this in seconds. Step-by-step + my prompt 🧵

@sama @rezoundous opus kind of gen x, gpt5.5 gen y and people acts like alpha to expect everything in return

@rezoundous curious, could you try to explain it?

Can't explain it, but I trust GPT-5.5 more than Opus 4.7 right now.

open source is the only way to learn from each other, actually the only way humanity work.

@MyCreativeOwls @Lovable @claudeai We already do this through the GitHub repository, like connect the repo via Lovable, create a work-tree on Claude Code and check the diffs, run an audit etc

How to connect @Lovable MCP Server to @claudeai in 60 secs Bookmark for later 🔋

@patrick_oshag What he said needs to be done by HR 😅 chill man!

Brian still spends over two hours a day on recruiting and personally hires the top 200 people at Airbnb. I loved this idea of being in the flow of talent to find the best people: "Don't do searches. Build pipelines. I try to map out all the best people in the Valley. So let's say I need to hire really good engineers. I don't do searches. I just informationally meet the best engineers in the world. Every meeting, the job is to get the next meeting, meet someone else. The mistake people make when they hire. They go, "I need to hire a blank." So they hire a search firm. They give you 50 profiles, and you pick the best one. That is the wrong way to do it. The best way to do it is pipeline recruiting. You're constantly recruiting, you're constantly meeting people. in advance of searches. And all of it is referral based. The two ways to find out if people are good – is to start with the results and work backwards to the people. Find an ad you like and figure out who made that ad. Start with the results. Work backwards to people. Don't start with the resume. The other thing to do is just keep asking people to build your Rolodex. The moment I find somebody that's really good, I ask them who all the best people they know are. And I build these little mafias and they tell you who the other good people are. I am the co-hiring manager for the top 200 people in the company. This is very radical. A lot of CEOs think it's their job to hire their executive team, and their executive team hires their team. I think that is fatal. You always want to be marrying up, hiring people of the future. It should be like we're reaching. If you can hire them without my help, we're not reaching far enough. You want to hire the very best person you can."

@yousaf_sbr @diegohaz almost same but audit is the most crucial part, so it should have done with both. The other thing is always save the patterns, knowledge in to project specific memory & rules, instructions etc. every pre audit and smoke test after implementation should be saved.

@thewebtailor @diegohaz What's the best way to use them both? I personally plan & audit with GPT, & implement it via Opus, what's your setup?

I gave the same task to GPT-5.5 xhigh and Opus 4.7 max. – GPT took ~30 minutes. – Opus took ~2 hours. Then I asked them to review each other's work and give an honest verdict on which was better. – GPT said its own code was better. – Opus said there was no obvious winner. Then I asked them to learn from each other and apply the best parts they had learned to their own code. In the end, I asked them to review each other again and give an honest verdict after they had both improved. – GPT kept saying its own code was better. – Opus said GPT's code was better. What a journey.

@BrianLaManna_ This is more like a mix of hidden gems and Michelin restaurant lists for San Francisco

Companies I'd consider going to if I ever had the urge to try something new. 1 Thinking Machines Lab 2 OpenAI 3 Anthropic 4 Cursor 5 Applied Intuition 6 Modal Labs 7 Decagon 8 Voyage AI 9 Cohere 10 Glean 11 LangChain 12 Ramp 13 Together AI 14 Fireworks AI 15 Cognition 16 Harvey 17 Scale AI 18 Warp 19 Hebbia 20 Rogo 21 Augment 22 Parallel Web Systems 23 Baseten 24 Brain Co. 25 Linear 26 Mercor 27 Mistral AI 28 Nuro 29 Adept 30 Vanta 31 Traversal 32 Metronome 33 ElevenLabs 34 Factory 35 Anyscale 36 Vannevar Labs 37 Abridge 38 The Browser Company 39 Reevo 40 Chalk 41 Nominal 42 Cartesia 43 Pinecone 44 Hex Technologies 45 Merge 46 Whatnot 47 Eventual 48 Faire 49 Arena 50 Bedrock Robotics List courtesy of Paraform's Talent Density Rankings. paraform.com/talent-density…

bir öykü, yeni kitap ☺️

@AbelGe87 In my humble experience as an NBA viewer, this is the worst coaching I've ever seen. It was a complete destruction operation targeting a young star.

Why does he gas out? Maybe because he's out there playing offense like he's a perimeter player, he has to work so hard to get his own shot off, he was top 14 in the league in unassisted field goals made which is not normal at all for a center

@Yuchenj_UW something you say amazing but never really use

Figma stock 20 minutes after the Claude Design announcement. Wild.

1972 ➡️2026 Apollo 17 ➡️ Artemis II

İyi Bayramlar 🍬 - mailchi.mp/13885532d135/r…

A week’s worth of work 🗓️ On 29 July 1888, Van Gogh wrote to his brother Theo about this painting of a young girl in Arles. He explained, ‘It took me my whole week (…). But in order to finish off my mousmé I had to save my mental powers.’ In the novel ‘Madame Chrysanthème’ by Pierre Loti, ‘mousmé’ refers to a young Japanese girl. Van Gogh read the novel and was fascinated with Japanese culture and art, as were many artists at the time. This portrait was inspired by the character in the novel. 🖼️ ‘La Mousmé Sitting’, 1888 © National Gallery of Art Washington D.C

8 Mart’ta Zorba’da @ugurterzi okurlarıyla buluşuyor🙋‍♀️🌿🌸

Meet a translation powerhouse that bridges Turkish and English. This model transforms Turkish text into fluent English with impressive accuracy. It's a go-to tool for anyone working across these languages.

L’été Van Gogh

Holy shit. The guy who BUILT Claude Code just shared his actual workflow. Boris Cherny runs 10-15 Claude sessions in parallel every single day. While you're prompting one AI, he has 5 in his terminal + 5-10 on the web all shipping code simultaneously. And the real weapon? His CLAUDE.md file. Every time Claude makes a mistake, the team adds a rule so it NEVER happens again. Boris literally said: "After every correction, end with: Update your CLAUDE.md so you don't make that mistake again." Claude writes rules for itself. The longer you use it, the smarter it gets on YOUR codebase. His other insane detail: he hasn't written a single line of SQL in 6+ months. Claude just pulls BigQuery data directly via CLI. Claude Code now accounts for 4% of ALL public GitHub commits. Engineers who haven't set this up yet are already behind. This CLAUDE.md template is the difference between using AI as a chatbot vs using it as a fleet of senior engineers. Drop it in any project. Free.

🚨 Anthropic just dropped 6 FREE AI courses that make most “AI degrees” look outdated. They quietly dropped 12 FREE courses that teach you how to actually build with Claude in 2026: • Make real API calls and ship tool-using agents • Build and deploy full RAG pipelines • Connect models to live tools and data with MCP • Spin up production-grade MCP servers with logs + scaling • Run Claude inside Amazon Bedrock and Google Vertex AI • Automate dev work from the CLI with Claude Code • Integrate GitHub, workflows, prompt scoring, multi-turn agents This is the stack serious builders are learning while everyone else is still arguing about prompts. If you’re not learning agent workflows and Model Context Protocol this year, you’re already behind.