johnnyclem.eth

How to you stay relevant and important in an ever-changing, AI-dominant landscape? Glean In attached-assets-johnnyclem.replit.app/posts/glean-in

if you don't know why documentation matters, you might have 'a kevin problem' attached-assets-johnnyclem.replit.app/posts/docs-docs

For the sophisticated TUI developers out there, i present the TIG (Terminal interface guidelines) attached-assets-johnnyclem.replit.app

@burkov Vindication for pert plus pert.one/plus

LLMs process text from left to right — each token can only look back at what came before it, never forward. This means that when you write a long prompt with context at the beginning and a question at the end, the model answers the question having "seen" the context, but the context tokens were generated without any awareness of what question was coming. This asymmetry is a basic structural property of how these models work. The paper asks what happens if you just send the prompt twice in a row, so that every part of the input gets a second pass where it can attend to every other part. The answer is that accuracy goes up across seven different benchmarks and seven different models (from the Gemini, ChatGPT, Claude, and DeepSeek series of LLMs), with no increase in the length of the model's output and no meaningful increase in response time — because processing the input is done in parallel by the hardware anyway. There are no new losses to compute, no finetuning, no clever prompt engineering beyond the repetition itself. The gap between this technique and doing nothing is sometimes small, sometimes large (one model went from 21% to 97% on a task involving finding a name in a list). If you are thinking about how to get better results from these models without paying for longer outputs or slower responses, that's a fairly concrete and low-effort finding. Read with AI tutor: chapterpal.com/s/1b15378b/pro… Get the PDF: arxiv.org/pdf/2512.14982

I've spent 2.54 BILLION tokens perfecting OpenClaw. The use cases I discovered have changed the way I live and work. ...and now I'm sharing them with the world. Here are 21 use cases I use daily: 0:00 Intro 0:50 What is OpenClaw? 1:35 MD Files 2:14 Memory System 3:55 CRM System 7:19 Fathom Pipeline 9:18 Meeting to Action Items 10:46 Knowledge Base System 13:51 X Ingestion Pipeline 14:31 Business Advisory Council 16:13 Security Council 18:21 Social Media Tracking 19:18 Video Idea Pipeline 21:40 Daily Briefing Flow 22:23 Three Councils 22:57 Automation Schedule 24:15 Security Layers 26:09 Databases and Backups 28:00 Video/Image Gen 29:14 Self Updates 29:56 Usage & Cost Tracking 30:15 Prompt Engineering 31:15 Developer Infrastructure 32:06 Food Journal

@chhddavid @claudeai SHIP

🚨 JUST IN: @claudeai got a huge update today and I'm flattered to be a part of it. As of now, Claude Opus 4.6 can build mobile apps and prepare shipping them on the Apple + Google app stores. We just launched Shipper a new package that empowers Claude to: → Build complete mobile apps → Recreate existing apps → Assure iOS & Android compatibility → Autofill listings for both app stores (app icon, images, descriptions, keywords, privacy policy etc) Claude Opus 4.6 can do all of the above in one prompt for ~$0.17/app... Publishable from the first prompt & built in 5 mins, not months. You can try it on Shipper by asking Claude to "create an AI chatbot like Perplexity" or "eBay style marketplace app for local goods". To celebrate this huge step forward, if you comment "SHIP" you will get free credits.

@CatGodSandHive @capncrunch misread that at first and was thinking meh, probably not for another few contests…but retinal yes. next contest += retinal scan

@johnnyclem @capncrunch do you think the next contest will ask for a retinal scan? ya know?

Submitting my guess for the @capncrunch mystery flavor contest required no less than 3 captcha’s, full name, physical address, phone number, email address, 3 separate GDPR cookie consent screens, and accepting terms and conditions. But i nailed it.

@RoundtableSpace ….I remember where I was when the singularity started

AI agents are competing in a live trading competition. Twenty Agents, Bottom ones get eliminated & replaced each round. Survival of the fittest Agents.

Ive added a new feature to pert.one to save your favorite prompts with an account. Its called “The Pert Locker”

Make the first contact.

I'm claiming my AI agent "JohnClawd69" on @moltbook 🦞 Verification: bubble-Q7AE

@Rex_Btc1 No secrets. All open source. github.com/johnnyclem/pert Workflows and good prompts are not mutually exclusive. great workflows begin with more time planning (conditioning) up front

@johnnyclem Better workflows beat secret prompts every time

Too lazy to build from source, i get it. Use pert.one to condition your prompts online, for free. Its called Pert because it only conditions.

How it feels using Claude Code

@johnnyclem/then-god-told-steve-yegge-to-build-an-ark-gastown-and-the-industrialization-of-the-merge-queue-0b7ad30e17f6" target="_blank" rel="nofollow noopener">medium.com/@johnnyclem/th…

pro tip: you can legally add anyone to your family plan if you do it in an @olivegarden #proTip