Drafts

I’m tracking results of 2026 Predictions [1] more open source, less open contribution # [2] 2026 is not the year to build hardware # [3] Agents will overwork us # [4] The AI Vampire This was an unusually hard post to write, because it flies in the face of everything else going on. Medium · steve-yegge.medium.com [5] 2026 is to ai as 2012 was for js frameworks # [6] References: [1]: /2026-predictions/ [2]: #more-open-source-less-open-contribution [3]: #2026-is-not-the-year-to-build-hardware [4]: #agents-will-overwork-us [5]: https://steve-yegge.medium.com/the-ai-vampire-eda6e4f07163 [6]: #2026-is-to-ai-as-2012-was-for-js-frameworks

🌱 This post is still growing b249c794-9411-42c0-be01-07922c3e98da.mp4 [1] a scroll through of https://github.com/WaylonWalker/markata-go/pull/1021 References: [1]: https://dropper.wayl.one/file/b249c794-9411-42c0-be01-07922c3e98da.mp4

🌱 This post is still growing Late last year I started writing I'm Out On Agents [1]. Agents sucked, the models were good, but there was still something missing between the harnesses and the models. They could write good code, they could do some debugging and exploring, but they were too good at fucking up the whole project to be useful. They could crank out Green Field POC’s like nobody’s business, but they created so much mess in brown field projects that it was easier to chat and edit yourself. f91a8893-b1ba-422a-9390-18de5034483c.mp4 [2] The Beautiful Glitch - Gemini The Inflection Point # [3] It’s very well agreed on that the inflection point for most people happened with Anthropic Opus 4.5 in late Nov 2025. Early adopters probably noticed right away and shouted from the rooftops how good it was. But we’ve all heard that developers have 6 months before ai writes all the code for years, so this felt like the rest of the noise. Hitting the December slowdown many of us hit cod...

I’ve been thinking about this for awhile, the AI wars are so much worse and burnout prone than the framework wars of the 2010’s. I remember really starting my professional programming journey during the framework wars. It was a time when there were new and exciting js things every single month. Frameworks and meta frameworks came and went, the ones that lasted changed best practices yearly or so, often flip flopping on technique. I was deep in python and data engineering at the time and only experienced it adjacently. I was into webdev. I did a bit of react, gastby, vue, gave all the big ones a try in a demo level.

Requirements # [1] - Minecraft - Terraria - SilkSong 3x6 layout # [2] ╭────┬────┬────┬────┬────┬────╮ │ │ │ │ │ │ │ ├────┼────┼────┼────┼────┼────┤ │ │ │ │ │ │ │ ├────┼────┼────┼────┼────┼────┤ │ │ │ │ │ │ │ ╰────┴────┴────┴────┼────┼────┼────╮ │ │ │ │ ╰────┴────┴────╯ Your browser does not support the video tag. [3] References: [1]: #requirements [2]: #3x6-layout [3]: https://dropper.waylonwalker.com/file/f5769ee4-7094-4527-a27c-c4b9f3d58bc2.mp4

Session ID: ses_3444b09b1ffeXTEr3ELFg5qqtg Created: 3/4/2026, 7:55:24 PM Updated: 3/4/2026, 8:52:32 PM --- User # [1] I want to spec out a cli for tmux session switching in go. - responsive to terminal size - works in tmux popup - shows list of tmux sessions with favorites pinned at the top keymap - j/k arrow navigation - tab to switch sections - asdfqwertzxcvb to pick a session (letter listed next to the session) - space to select a session, then arrows j/k move that session up in priority and hotkey letter --- Assistant (Build · gpt-5.3-codex · 2.4s) # [2] Thinking: Initiating brainstorming skill load Tool: skill Input: { "name": "brainstorming" } Output: <skill_content name="brainstorming"> # Skill: brainstorming # Brainstorming Ideas Into Designs ## Overview Help turn ideas into fully formed designs and specs through natural collaborative dialogue. Start by understanding the current project context, then ask questions one at a time to refine the idea. Onc...

Ansible Vault keeps secrets out of sight, but the ciphertext changes on every encrypt. That turns Git [1] diffs into noise and makes it hard to tell if anything actually changed. Decrypting, editing, and re-encrypting often leaves uncertainty about whether any plaintext changed. This is amplified when secret repos are tightly coupled to dependent repositories. A typical cycle includes decrypting, adding a key, updating a value, applying changes, and returning later with little clarity about what changed while secrets were in plaintext. Today a new workflow was created with @gpt-5.2-codex to keep diffs clean and avoid re-encrypting when the plaintext is identical. Chat-reply This repo has ansible vaulted secrets and an encrypt/decrypt process, but no way to compare. Please research compare options. The goal is to avoid changing files on encrypt/decrypt when plaintext is unchanged, ideally by comparing decrypted content and reusing the remote encrypted file. @gpt-5.2-codex The re...

I don’t know if you know this, but the web is a beautiful platform that allows you the freedom to create things and put them out there. Its not tied to four major platforms. You don’t have to post your thoughts, ideas, and apps to a platform, you can just make it. This is a beautiful thing that seems to have been forgotten. I was inspired this morning from @scotthanselman’s tinytooltown [1]. Looking through all of the tiny tools that people have built for themself, as personal software, not answering to anyone but themself, it was inspiring. Agents have gotten a lot better, like seriously better. The ai bros that were ai pilled too early that said SWE is over in six months called it too early. It wasn’t time. Now since Nov 2025 we have had agents that can do some damn work. Proving the point some of the greatest devs I’ve ever looked up to have not written a line of code since. Not hype bros or someone not good at the craft, but seriously good devs leaning on it full time. AI hype...

Is AI making us more productive yet, more faster yet? Non-code # [1] probably not I’ve seen this question hitting all over the Internet lately, and often points to people not writing code. Copilot turns prompts into emails, emails back into summaries that look a lot like prompts. I think there’s a place for this, making rambled thoughts sound more coherent, summarizing notes and meeting minutes. All good stuff but does it make us more productive, probably not by an amount that you can put $ $ behind, unless you are reducing headcount. thats not what we are doing right??? Coding # [2] with chat, probably not When we talk about chatbots like gippity I think there’s a benefit to having someone with jr skills in everything to talk to, someone who can read all of the docs in an instant to get you some code snippet that might have taken all day to research and get right, but more productive, probably not. Agentic Coding # [3] maybe I’ve hit a stride with coding agents this year u...

drafted by kimi /style How I write and build this site. A personal style guide. Tone of Voice # [1] Casually self-deprecating with technical credibility. I write like I’m talking to someone at a conference after-party, not a LinkedIn profile. It’s okay to poke fun at myself and my projects. “Under-funded, over-dreamed, barely documented” is a feature, not a bug. Principles: - Use first person (“I”, “me”, “my”) - Keep sentences punchy and direct - Include real personal details and hobbies - Show technical expertise without taking myself too seriously - It’s okay to mention frustrations with mainstream tools Writing Rules # [2] Formatting: - No em-dashes. Use periods or commas instead - No emoji - 80 character hard wrap - Double space between sentences - Headers should be concise (2-4 words) Structure: - Put code examples front and center - Add brief context or “why this matters” even if just one sentence - It’s okay to say “I use this when…” or “This saved me fr...

drafted by kimi /interests Things I’m passionate about and why they excite me. Mechanical Keyboards # [1] I’ve fallen deep into the custom keyboard rabbit hole. Building keyboards combines electronics, ergonomics, and 3D printing into one satisfying hobby. What I love about it: - Tactile feedback - Every keystroke has personality - Ergonomics - 40% split layouts changed how I think about typing - Customization - From switches to keycaps to case design - DIY culture - Hand wiring, firmware hacking, designing my own PCBs Current projects: - Building a split 40% wireless keyboard - 3D printing custom keycaps - Designing the “portajohn” keyboard case See my keyboard posts [2] 3D Printing # [3] From functional parts to artistic experiments, 3D printing lets me materialize ideas. What I print: - Keyboard components - Cases, keycaps, plate files - Practical tools - Knife sharpeners, microphone mounts, dovetail experiments - Kid projects - Working with Wyatt on various b...

Are developers really running 5 agents in parallel? How the Heck do they keep up with the changes? This seems Impossible. I was listening to Syntax.fm this morning and heard this question, and thought I’d throw in my take, which is probably pretty similar to Wes and Scott’s. https://www.youtube.com/watch?v=NrBQI9So5lM&list=PLLnpHn493BHHNUfHN5lDf11UD8jQ5Bpzl&index=1&t=99s [1] Yes # [2] Yes, developers are running 5 agents in parallel. It’s not that hard it requires you to shift from thinking about the weeds and seeing the forest see: Pm Not Babysitter [3]. It requires effort and diligence. Most importantly it requires planning, it requires agents, it requires tooling. Is anyone doing this all day? Probably not. At least not outside of the startup companies that are building out tools to do this. Yes there are some, there’s always outliers, but its going to be rare. To have multiple agents running in parallel add day you need a lot of tokens, access to good models, and right now ...

A running list of blog post ideas to strengthen underrepresented topics on the site. Docker Posts # [1] Building out Docker/containerization content to match the llms.txt claims. Existing Foundation # [2] - docker-deep-dive.md [3] - unpublished notes from 2021 - docker-minecraft-server.md [4] - minecraft in docker - modded-minecraft-in-docker.md [5] - modded server setup - emoji-in-headless-chrome-in-docker.md [6] - headless chrome fix Suggested Posts # [7] - “Why I containerize my entire dev environment” - Philosophy post linking to the 2026 resolution about working from a distrobox image - “Docker vs Kubernetes in the homelab [8]: when to use what” - Standalone comparison post (referenced in right/wrong reasons posts) - “My devtainer workflow: dotfiles in Docker” - Document the actual devtainer setup mentioned in llms.txt - “Migrating from Docker Compose to Kubernetes with kompose” - Experience from the 6-months-in post, expanded - Finish docker-deep-dive.md - Turn th...

I’ve been dabbling with go this week using

In early 2026 I’m trying to lean more in to agentic workflows. The tools are not only better than they were a year ago, but available to me now unlike they were 6 months ago. What I’m using # [1] At home I’m using opencode, the tooling here is fantastic. LSP incide of these things is incredible, mcp is fine when its needed. The free models it gives you are impressively good for free models, but they are still not the big models from the big providers. I’m using what work gives me, they give me a tool with access to good models, the models are great, the tools kinda suck. I’m being vaugue here because I dont share real work details. Skepticism # [2] I’ve been skeptical the whole way, I see ai being a very useful tool. I remain Techbrophobic [3]. It’s better than the non believers will tell you, and no where near as good as the hype bros will tell you. The industry is shitty and doing shitty things, I’m not here to change this, I’m here to do my thing and try to get better. Softw...

I’m late on this one so I’ve seen everyone else’s. I’ll try my best to make some bold predictions I’ve not seen elsewhere more open source, less open contribution # [1] I predict that this is the point in time that we see an explosion of open source, but more projects than ever going the way of sqlite, Livestream, android, unreal engine, aesprite. It is getting so easy for agents to generate 10k lines of code in a few hours. This makes it easy for folks who have ideas they want to create to create them. It also makes it much harder to accept outside contributions when they make such massive changes. Thirdly it will be easier for folks to just make their own fork to do what they want. Right now it’s hard to name 5 big open source, closed contribution projects by the end of the year there will be 5 more that are recognizable. I think more open contribution will go the way of [[ whenwords ]], spec driven development. This is very high level. Very easy to understand a large portion ...