Derek Organ @jeebers

It is my belief that many devs right now are not maximizing what they can do with automatic programming because they still look at the code. Doing it makes you the bottleneck. Your time is better invested in new ideas, QA, design, and asking yourself what is your goal.

My dev setup: two Claude Code sessions. Session 1 = Product Manger - Files GitHub issues only, never writes code. Session 2 = ‘/loop’ reads issues I label “ready”: build → /simplify → adversarial review by Codex CLI (GPT-5.5) → tests → PR → deploy w/ rollback & learnings

Was reading Monkey Puzzle to my 3 year old for bed time. I feel very much like the monkey lately building apps with Claude code. “No No No!!! …”

@eoghan @salesforce @fin_ai Amazing work guys! Congratulations

Claude Code not supporting `.agents/` for skills and stuff is annoyingly hostile 🫠

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.

Marc Andreessen on why the best founders don't hire, they convert believers. When you're a 3-person startup with no revenue, how do you convince top talent to choose you over Google or Microsoft? Marc's answer cuts straight to the heart of it: "The difference between a vision and a hallucination is that other people can see the vision." This is the real skill behind great hiring, and it has nothing to do with compensation packages. @pmarca points to Steve Jobs as the ultimate example. He describes what he calls Jobs' "reality distortion field": "If you get within 10 ft of Steve Jobs, whatever he says the next 20 minutes, you're going to walk out of there believing whatever he says. He can say the sky is purple and you'd be like, 'Yep, that makes total sense.' And 4 hours later you're like, 'Well, I don't really know what he meant by that, but it was really, really compelling at the time.'" That's the superpower the best founders share. They can describe where the world is going with such clarity and conviction that people don't just understand the vision. They feel it. They want to be part of it. As Marc puts it: "It's essentially sales. Selling to employees." But here's the counterintuitive part about hiring that Marc has observed over the years: The frustration is actually doing exactly what it's supposed to. When a candidate turns you down after multiple conversations, it stings. It feels like wasted time. But Marc reframes it: "Of all the people you interview, if you hired them all, it would turn out that a good two-thirds or three-quarters of them you probably shouldn't have hired anyway." Rejection is the selection process working exactly as it should. The best companies lean into this by presenting a brutally honest picture of who they are. Not a polished recruitment pitch, but a stark and polarising reality, and that clarity of identity is what makes the right people self-select in. "If in your hiring process you're turning people off as often as you're turning them on, I think that's a good thing." Stop trying to convince everyone. Be so specific about who you are and where you're going that the right people find you, and the hiring problem starts to solve itself.

An AI CEO finally said something honest... youtu.be/ZM2c33qy16U?is… via @YouTube

It is fascinating to what degree the coding agents are starving for data Give it production data, open source, good docs, and a push and it flies Poorly spec it, say a few words and ignore it, and you still get non functioning boilerplate

@SebJohnsonUK Things defo could be better and we should act however. The point when you need to raise money you go to the US because more VCs but also and very importantly the US is where the customers are. It’s the biggest market

Vibe Coding Is the New Product Management “There’s been a shift—a marked pronouncement in the last year and especially in the last few months—most pronounced by Claude Code, which is a specific model that has a coding engine in it, which is so good that I think now you have vibe coders, which are people who didn’t really code much or hadn’t coded in a long time, who are using essentially English as a programming language—as an input into this code bot—which can do end-to-end coding. Instead of just helping you debug things in the middle, you can describe an application that you want. You can have it lay out a plan, you can have it interview you for the plan. You can give it feedback along the way, and then it’ll chunk it up and will build all the scaffolding. It’ll download all the libraries and all the connectors and all the hooks, and it’ll start building your app and building test harnesses and testing it. And you can keep giving it feedback and debugging it by voice, saying, “This doesn’t work. That works. Change this. Change that,” and have it build you an entire working application without your having written a single line of code. For a large group of people who either don’t code anymore or never did, this is mind-blowing. This is taking them from idea space, and opinion space, and from taste directly into product. So that’s what I mean—product management has taken over coding. Vibe coding is the new product management. Instead of trying to manage a product or a bunch of engineers by telling them what to do, you’re now telling a computer what to do. And the computer is tireless. The computer is egoless, and it’ll just keep working. It’ll take feedback without getting offended. You can spin up multiple instances. It’ll work 24/7 and you can have it produce working output. What does that mean? Just like now anybody can make a video or anyone can make a podcast, anyone can now make an application. So we should expect to see a tsunami of applications. Not that we don’t have one already in the App Store, but it doesn’t even begin to compare to what we’re going to see. However, when you start drowning in these applications, does that necessarily mean that these are all going to get used or they’re competitive? No. I think it’s going to break into two kinds of things. First, the best application for a given use case still tends to win the entire category. When you have such a multiplicity of content, whether in videos or audio or music or applications, there’s no demand for average. Nobody wants the average thing. People want the best thing that does the job. So first of all, you just have more shots on goal. So there will be more of the best. There will be a lot more niches getting filled. You might have wanted an application for a very specific thing, like tracking lunar phases in a certain context, or a certain kind of personality test, or a very specific kind of video game that made you nostalgic for something. Before, the market just wasn’t large enough to justify the cost of an engineer coding away for a year or two. But now the best vibe coding app might be enough to scratch that itch or fill that slot. So a lot more niches will get filled, and as that happens, the tide will rise. The best applications—those engineers themselves are going to be much more leveraged. They’ll be able to add more features, fix more bugs, smooth out more of the edges. So the best applications will continue to get better. A lot more niches will get filled. And even individual niches—such as you want an app that’s just for your own very specific health tracking needs, or for your own very specific architectural layout or design—that app that could have never existed will now exist.”

1. When you write something intended to be read by an important person, go through it and cut every unnecessary word. 2. The reader of anything you publish is an important person.

Programming is now 10x more fun with AI.

@zcabrams But what if it’s nature not nurture that’s the reason?

@UtdChapters Mesut Özil

@ESPNUK Wilde blew up with 1k to go

For anyone who missed this live, here it is from start to finish: - Chris O’Donnell (46.09) - Rhasidat Adeleke (49.53) - Thomas Barr (44.90) - Sharlene Mawdsley (49.40) (3:09.92) National Record ☘️ European Gold 🥇

MVP is over. You need to think about Minimal Viable Experience. buff.ly/3xCpRYo

@multikev Love it! We ask ChatGPT to tell my three year old new bedtime stories she comes up with ideas for and then make a picture that represents the story after. Just some:

keyboard_arrow_left Previous keyboard_arrow_right Next

The Cost of Cloud, a Trillion Dollar Paradox a16z.com/the-cost-of-cl…