Blog

Listening to this video and feeling inspired. Its crazy how the Conference AI Engineer feels like such a hype bro conference ready to tell you just do more, let go, you’re cooked if your not on the train, gaslighting you to believe something they lack evidence in. But what it really is, is a group of talks that are done by some of the best engineers trying to make it through this transisition just like the rest of us. Drawing the lines between the past and the current. How do you get comfortable with the current without letting go, without giving in to shipping slop, but shipping real good work with confidence. https://youtube.com/watch?v=Se8jHLliLXE It turns out that good Developer Experience is also good Agent Experience testing continuous integration continuous delivery local development Monitoring with logs, spans, and traces Can you to the best of your ability say what you are about to ship is of high quality and provides new features with fewer bugs? Can you see bugs in productio…

I’m I watched through this video earlier of this guy roasting t3.gg and his level of agentic ai brain rot. https://youtube.com/watch?v=ZumXpZzDsgo I really do think this guy had a lot of valid comments about people not being able to look at long form content, not being able to focus long enough to read a page of ai output. Loosing our ability to think critically. He points to some of t3.gg videos at certain points where Theo says, I’m not even going to read this I’m going to have the agent xyx and move on. The guy roasting Theo seems like a really smart guy, an academic kind of guy. A guy that really values knowledge. Mad props for this and his ability to avoid the brain rot. I think we have a lot of folks out there that are talking the talk without walking the walk. This guy seem s genuine. He seems like he really knows what he is talking aboutt and that he is still reading and writing every line of code themself. I think we still need people that can carry this torch. Its going to be…

I heard Lex Friedman talk about this method he uses to create Greenfield apps really fast and he claimed worked really well with the latest Gen models at the time. This was during the DHH round 2, 5 hour interview. Lex asked if DHH uses voice chat at all. DHH claimed it was too uncanny for him. Too weird. He said he still likes to feel like he is chiseling out something by hand. He has interacted with a computer for a quarter of a CENTRUY to write open source code by typing into it with a keyboard, and it feels weird to talk to it. Lex went on to say next time you have a greenfield project, something you want to come out good somewhat specific for you, and not have to fuss with it, turn on the mic and just word vomit for 20 minutes. The models do surprisingly well at this. Today I was feeling the weight of 20 or so PR’s opened up mostly by agents awaiting my review. This whole things sits on my shoulders. I’m the one that gets the calls when its down, and I’m the one with the final say…

Recent Arch linux vulnerabilities are a good reminder of a few things. AUR is not the official package repo The AUR is community driven AUR packages are not always safe The first thing I’m doing to stop myself from running any aur updates automatically is removing any arch helper. Currently the reported vulnerabilities are supply chain attacks limited to the aur, keep your arch system up do date, BUT do not update packages from the AUR right now. In fact I’m auditing my aur usage and removing anything I have not used in awhile. Here is a nice script I’m using to walk through my packages and get rid of things I installed and probably don’t need anymore. Supply chain attacks are getting real scary in 2026, maybe we should listen to Ginger Bill a bit closer.

I was listening to @syntaxfm this morning and @wesbos said at 328s “The prompt seagulls are driving me nutty”. 100% hard agree Wes. Now I didnt just come off of a conference where they dropped fable 5. I’ve not logged into twitter in months, but I see it around work. prompt-seagulls “Prompt, PR-ompt, promt, PROMT” There is no such thing as magic # Asking for the prompt as a first question here, is a clear sign you are looking for magic. What are the magical incantations I must pass to all master clanker to get it to do the things that I want. Wrong, there is no magic prompt to get impressive results, its people that know and understand their craft that get amazing results. They have taste. They have design in mind, They see what the end product should be. They are guiding the model to do what they want and are not surprised when they get it. prompt-seagulls “Prompt, PR-ompt, promt, PROMT” process # No one is one shotting their work and kicking up their feet for the other 39 3/4 hours o…

Agentic coding has this nice trick of letting you bang out a project in an afternoon, something complex that would have take some real time to implement, not just some rounding error that can slip right in between the jira board. Then it will be perpetually never done. There will always be bugs and thorns rear their head up, new features no one ever thought of, and now no one really has to think much about beyond having the idea. This part of software engineering has always been here, its the root of the never complete 200 side projects. But now it feels like fuel has been poured on the fire, like we can get more done than ever. But we are tricking ourselves, these projects will never be “done”. There’s always more to add. Without feeling any of the pain of implementing it yourself, why not just keep adding new features forever. This is the mentality that is crushing me right now. It pulls at your token anxiety like crazy. You look at the usage board and you are almost cooked so you sw…

EDC # I try to keep a pretty light every day carry, but it never works out, keyfobs and headphone cases end up causing more bulk than I’d like, but My EDC is no where near the bulk I had as a kid with my cargo pants decked out with everything I could possibly need. I hold no attachment to anything in my EDC. Nothing on my person has sentimental value. Anything I carry can be lost, stolen, or destroyed at any point in time. I pick things of sufficient usable, utilitarian, quality sufficient to work. No extra fluff. Google Pixel 6 Ridge Wallet Olight Perun - Since April 2022 Civivi Qubit - Since March 2024 after my last one was donated to the Indianapolis Stadium OpenFit Shokz Rules # lightweight replacable no emotional attachments utilitarian everything serves a purpose My kit # Phone # Google Pixel 6 I will not get finance a new phone for the foreseeable future again. The last time I feel like I got a phone that felt like an upgrade was 2018 when I went to the Pixel 3. The pixel 6 and…

I’ve been thinking about this for awhile now. For years now, fuzzy pickers and last session have been my go to. They have served me well. I can typically only keep so much in my head anyways. I’m often doing a hub and spoke pattern between main project, notes, and infra repo, maybe two projects. Don’t get me wrong, I regularly run with a dozen or more sessions running at a time, but only two to three are in my immediate context at any point anyways. The Design # harpoon for tmux press a hotkey followed by one more keystroke, currently any left hand letter SIMPLE, FAST, thats of utmost importance, what I want are sessions that I can can be assigned in order of importance from middle row, top row, bottom row. I added this binding to my tmux config. Now I can press to go to the first session, to go to the second session. and pause to think j/k to navigate, space to pick up a session and move it, x to kill it. Enter the agents # Now with agents doing more and more work, and cooking for lon…

Inspired by @mollywhite’s verify slashpage. This page serves as the system of record for my online identity. The best places to follow me are: My Website: waylonwalker.com YouTube: Waylon Walker YouTube Gaming: Waylon Walker Gaming Twitch: Waylon Walker Twitter: @_WaylonWalker LinkedIn: Waylon Walker GitHub: WaylonWalker Dev.to: Waylon Walker Bluesky: @waylonwalker.com

Definitive ranked lists of my top 3 favorites plus an honorable mention. Terminal Tools # neovim - modal editing changed how I think about text tmux - terminal sessions that survive disconnects and allow me to hop between projects at the speed of thought. k9s - S tier tui interface that all tuis should strive for Honorable mention: ipython Python Tools # pandas - This is what got me out of corporate spreadsheets and back into code/software. kedro - data pipelines with opinions I agree with fastapi - my favorite python web framework Honorable mention: typer - fast cli apps Games to Play with Kids # multiplayer Minecraft - infinite creativity, modding potential Wobbly Life - Open World Co-op Stardew Valley - cozy, collaborative farming Honorable mention: Terraria - 2d world builder Games to Play Alone # singleplayer Hollow Knight / Hollow Knight Silksong - S tier 2d platformer with adventure, mystery, lore, boss fights. Session Skate Sim - The best skate sim Animal Well - epic 2d platfor…

Inspired by @fyrio’s yep slashpage, a list of S tier things I enjoy, use, recommend, want to know more about, or seek out in no particular order, updated as I think about it. Seealso /nope Inspired by @baty 's nope slashpage, a list of ** things I don't like, don't care, avoid, overhyped, or won't do in no particular order, updated as I think... Feb 11, 2026 /yep # coffee small web 1.0 RSS minecraft Hollow Knight Silksong terminals python vim keybindings self-hosting open source running kubernetes in my basement mechanical keyboards markdown data engineering Woodworking Fingerboarding Darts Skateboarding Biking Trampoline 3d printing

Inspired by @baty ’s nope slashpage, a list of F tier things I don’t like, don’t care, avoid, overhyped, or won’t do in no particular order, updated as I think about it. Seealso /yep Inspired by @fyrio's yep slashpage, a list of ** things I enjoy, use, recommend, want to know more about, or seek out in no particular order, updated as I... Feb 11, 2026 /nope # roblox mobile games telemetry Windows VSCode allow notifications subscription hell ads social media clickbait WYSIWYG editors particularly ones that use proprietary non text formats politics short form video

Stop babysitting your agents, treat them like a real team and they will reward you. Back in December I saw theo make a comment that code is now cheap, its the run rate of models, He quoted a study, not sure that he fully even believed it, but it claimed that the average developer after all meetings, training, emails, planning and extra shit in their day averages out 10 well tested lines of code per day. Opus 3.5 made him 10k loc (lines of code) that day. We have all agreed for decades that lines of code is not a proxy to productivity or quality. Often more code means more risk, more review, more infrastructure. This has become MUCH different. Lines of code are still far from any sort of good metric. That aside, your agents are not doing 10k lines with you babysitting them, and in fact its very likely that the product quality is MUCH worse as you babysit them. You need a tool for planning and tracking, otherwise you are playing babysitter rather than Product Manager (PM).

The state of development in early 2026 is all wrapped around learning how to manage many agents running in parallel. Everyone’s trying to figure out the workflow. The Plan Is Everything # The secret I’ve discovered is a good, well-defined plan. This could be a markdown file or a GitHub issue. Agents are actually great at writing these for you. They’ll include reproduction steps, outline changes needed, and structure the work. This is your opportunity to step in. Read the plan. Look for hallucinations. Spot where it’s going off track. Edit the plan before the agent starts coding. I had one today where it laid out reproduction steps beautifully, but I could add context about network requests that completely changed the approach. This editing phase is what most people are missing right now. Skip it and you’ll watch your agent solve the wrong problem with impressive efficiency. The Pace Problem # Here’s what nobody warned me about: managing these things is exhausting. Depending on the day,…

I was listening to these guys talk about migrating off of boomer ai the other day. Introducing the term boomer ai to describe using chat, copy, paste instead of agents. Something magical happened to the tooling and models around december, they got really good. The chatgpt $20 plan hooked into opencode is good, the Free models in Opencode Zen (Big Pickle and Kimi K2.5 Free) are really good. Neither of these quite match up to the speed and quality of the larger plans, but they are good. good enough to throw away your boomer ai techniques and start using agents. Agents are the future, and they are here now. If you are still using chat, copy, paste, you are doing it wrong. Stop using boomer ai and start using agents. You will be amazed at how much better your results will be. https://www.youtube.com/watch?v=3dmPKuTWbsI

I can now just mention people from my markata Waylon Walker Blogroll like @simonwillison or @swyx.io /now /now /now Aside This is an aside!

open code - libre free as in beer and speech Copilot - corporate 9-5er Cursor - You sip on Philz coffee with your macbook Claude Code - Agentic Workflows or Bust Jetbrains - I didn’t know you wrote java Vim/neovim - definite neck beard VsCode - What else is there?