Bora

{Global build week} @vercel ▲ We are hosting Zero to Agent event in Istanbul. Friday, April 24. 5:00 PM. Come ship with us. luma.com/17jrf20j — ​Zero to Agent is a global build week where we ship real AI agents with v0 and Vercel. All submissions go into the global competition at Vercel Community with $6K+ in prizes.

Understanding the logic behind biases allows us to confront, moderate, and potentially use them positively. This directory takes a swift dive into various cognitive biases affecting our lives and work, aiming to help us design with greater awareness. 1984.design/psychology-of-…

The debate over which additional skills designers should acquire; such as coding, writing, or understanding business is ongoing, with differing opinions on their necessity. However, one crucial skill every designer should possess is a solid understanding of psychology. Because only psychology provides insights into how humans perceive and interact with their surroundings, essentially offering a blueprint for our behavior. By incorporating psychological principles into design, we can create products and experiences that are more intuitive and tailored to human needs. Rather than imposing designs on users, we can design with an understanding of how people naturally think and behave. Explore the free library I’ve built over the years, including 110+ articles. The literature on cognitive biases and heuristics is extensive, but this directory contains user-friendly summaries and applications in digital products with resources. Central to this section is how cognitive heuristics and biases influence our decision-making, but you will also learn more about how to overcome them.

Because attention determines what will or will not appear in consciousness, and because it is also required to make any other mental events—such as remembering, thinking, feeling, and making decisions—happen there, it is useful to think of it as psychic energy. Attention is like energy in that without it no work can be done, and in doing work it is dissipated. We create ourselves by how we invest this energy. Memories, thoughts, and feelings are all shaped by how we use it. And it is an energy under our control, to do with as we please; hence, attention is our most important tool in the task of improving the quality of experience. — Flow by Mihaly Csikszentmihalyi

Creator.

@jakedugard 🤔 @bookmarkercc

I vibe coded a Figma plugin for browsing Arena channels without leaving your canvas called ⁂ Asterism. Submitted it officially through Figma but it's taking a while, so releasing a beta. Link below.

@karpathy I've done this for bookmarks, you can talk your library, explore and rediscover stuff through your Assistant, expand via web search inside the app. bookmarker.cc/about

LLM Knowledge Bases Something I'm finding very useful recently: using LLMs to build personal knowledge bases for various topics of research interest. In this way, a large fraction of my recent token throughput is going less into manipulating code, and more into manipulating knowledge (stored as markdown and images). The latest LLMs are quite good at it. So: Data ingest: I index source documents (articles, papers, repos, datasets, images, etc.) into a raw/ directory, then I use an LLM to incrementally "compile" a wiki, which is just a collection of .md files in a directory structure. The wiki includes summaries of all the data in raw/, backlinks, and then it categorizes data into concepts, writes articles for them, and links them all. To convert web articles into .md files I like to use the Obsidian Web Clipper extension, and then I also use a hotkey to download all the related images to local so that my LLM can easily reference them. IDE: I use Obsidian as the IDE "frontend" where I can view the raw data, the the compiled wiki, and the derived visualizations. Important to note that the LLM writes and maintains all of the data of the wiki, I rarely touch it directly. I've played with a few Obsidian plugins to render and view data in other ways (e.g. Marp for slides). Q&A: Where things get interesting is that once your wiki is big enough (e.g. mine on some recent research is ~100 articles and ~400K words), you can ask your LLM agent all kinds of complex questions against the wiki, and it will go off, research the answers, etc. I thought I had to reach for fancy RAG, but the LLM has been pretty good about auto-maintaining index files and brief summaries of all the documents and it reads all the important related data fairly easily at this ~small scale. Output: Instead of getting answers in text/terminal, I like to have it render markdown files for me, or slide shows (Marp format), or matplotlib images, all of which I then view again in Obsidian. You can imagine many other visual output formats depending on the query. Often, I end up "filing" the outputs back into the wiki to enhance it for further queries. So my own explorations and queries always "add up" in the knowledge base. Linting: I've run some LLM "health checks" over the wiki to e.g. find inconsistent data, impute missing data (with web searchers), find interesting connections for new article candidates, etc., to incrementally clean up the wiki and enhance its overall data integrity. The LLMs are quite good at suggesting further questions to ask and look into. Extra tools: I find myself developing additional tools to process the data, e.g. I vibe coded a small and naive search engine over the wiki, which I both use directly (in a web ui), but more often I want to hand it off to an LLM via CLI as a tool for larger queries. Further explorations: As the repo grows, the natural desire is to also think about synthetic data generation + finetuning to have your LLM "know" the data in its weights instead of just context windows. TLDR: raw data from a given number of sources is collected, then compiled by an LLM into a .md wiki, then operated on by various CLIs by the LLM to do Q&A and to incrementally enhance the wiki, and all of it viewable in Obsidian. You rarely ever write or edit the wiki manually, it's the domain of the LLM. I think there is room here for an incredible new product instead of a hacky collection of scripts.

Source: Design Is an Instrument of Strategy baytas.net/blog/instrument

Designers are good for your business. If you're not using design as an instrument for strategy at your startup, you're leaving money on the table. @doctorbaytas

@scspeier 612 contributions so far and counting. 🫡

Over the past two months, my most impactful move as a design manager has been encouraging and supporting every designer to start building with Claude Code. Designers used to create a “source of truth” in Figma which was used for QA and accountability.. if anything was wrong, you’d point to the designs and say, “This is how it’s supposed to look.” The designers would take this artifact hand it off to engineers to build another “source of truth” on GitHub that would become the repo where other engineers can fork and build on top of. Now — the designer creates the source of truth on GitHub, and it’s closer to “the designs” because it is the designs. Less gets lost in translation, and everyone speaks in code. Figma remains useful for napkin sketches and quick visual experiments, but we are clearly moving beyond Figma as the primary document. The hardest part is getting set up—it’s daunting and scary leaving the things you love behind. People just need a little bit of emotional support to get started. But after taking the leap, everyone is feeling empowered and excited. They are all literally 10x’ing their productivity. The worst part is that engineers are a bit overwhelmed because they have way more PR’s to review.

From the Academy Award®-winning filmmakers behind Everything Everywhere All at Once and Navalny; a father-to-be tries to figure out what is happening with all this AI insanity. The AI Doc: Or How I Became an Apocaloptimist is a hand-made, eye-opening documentary about the most powerful technology humanity has ever created... and what’s at stake if we get it wrong. focusfeatures.com/the-ai-doc-or-…

“The scariest movie of the year, except it's a documentary.” youtube.com/watch?v=xkPbV3…

@iamncdai @shadcn Beautiful. Recently published an article on @Substack about its creator @SusanKare designexplained.substack.com/p/designer-por…

Apple Hello Effect – Spanish Install with @shadcn CLI npx shadcn add @ncdai/apple-hello-effect-spanish

@taherdhanera "the best" "the hottest" "most successful" x this y that. enough of this language and constant comparison with others. we should keep our focus on thinking, building and shipping features that provide users value.

Codex is on fire right now. It’s the hottest and most successful coding agent in the game. What makes Codex special is the leadership behind it. Sharp minds. Clear vision. Just pure building energy. Big shoutout to the people holding it down and pushing the community forward every single day. You guys are not just managing, you’re shaping the future. @romainhuet @thsottiaux @dkundel - my Favourites.. These guys are not just part of the system. They are driving it. Day by day, step by step, making Codex better, faster, stronger. You can feel their impact. building has never been this easy. You just need to start. We are living in a time where dreams are not just dreams. They are drafts waiting to be shipped.

@karunkaushik_ TV series about startup failures 👀 Explore how risky business models and unethical startup practices impact entrepreneurs. Discover why responsible leadership and sustainable growth matter for building lasting companies. 1984.design/blog/tv-series…

There’s been a lot of allegations against Delve. But we haven’t been able to share our side of the story until today due to ongoing cybersecurity and forensics investigations. Maintaining customer trust is central to everything we do. That said, we grew too fast and fell short of our own standard. To our customers, we deeply apologize for the inconveniences caused. We take these allegations seriously and have made changes: a new auditor network, free re-audits and pentests for all customers, enhanced transparency in audit communications, and more. However, we also want to set the record straight on the anonymous attacks. The evidence we have points to a targeted cyberattack from a malicious actor, not a “whistleblower.” We believe the attacker purchased Delve under false pretenses, exfiltrated internal company data, and used it to launch a coordinated smear campaign. The posts rely on a mix of fabricated claims, cherry-picked screenshots, and stolen data taken out of context. See the link in the comments for more details. Delve was built to modernize compliance. We are not going anywhere and are committed to building what's next.

On my radar @noondesign 👀

That's us! 🌍 The Artemis II crew captured beautiful, high-resolution images of our home planet during their journey to the Moon. As @Astro_Christina put it: "You guys look great."

This is how you design a typographic poster. 👏

macOS Tahoe 26.4 — software update. "This update introduces 8 new emoji, along with other features, bug fixes, and security updates for your Mac." Still no fix for the poor corner radius alignment. Does anyone know a way around this? 😕 I've managed to hide confusing icons in menus and simplified the view with the following terminal command: defaults write -g NSMenuEnableActionImages -bool NO Source: 512pixels.net/2026/03/hide-m…

@ashebytes 🖤

"everyone has a podcast ashe" I don't care. I love making my aesthetic videos with my brilliant friends, listening to them intently as they describe working hard on some frontier, in a beautiful place. I love sharing it out with you all. my life as a godard movie. for the female gaze. do the thing for you because you stand by it as a person because you love it