Thoughts

Casey had an interesting point here. I think demitri came back with some sense of sanity that its just not how corporations look at employee cost, but I still thought it was a head scratcher.

Roughly translated not quoted

If the sellers of ai are telling you that your developers are going to be 10x productive, why are they only spending half their salary in tokens? Why not 9x?

I hate how he called out terminal user interfaces as shit… then proved web interfaces to be superior. Damn him. I love working from my terminal, but having ai prove itself through html reports including video, image, metrics, charts, and text is goated. Rethinking yourself has the bottleneck not the orchestrator feels real. Validating the work is hard, theres a shift right now and everyone is trying to figure it out. Lucas’s technique is a little bit of be lazy and tell it to prove itself to you, so as you juggle your 15 agents you have a nice report to read.

This is a really good guide, with quite a few good nuggets. I need to try deleting my AGENTS.md and rebuilding it from scratch more often. I liked how he talked about having agents prove their work and tell them up front how they will be judged. What I didn’t care for so much was the feeling that a lot of the rules go in markdown, thats not a rule, thats a suggestion. Rules should be deterministic. They should be tests and linters that ensure they are followed. Suggestions are good, but dont trust the agents to always follow them. And don’t trust that they wont change your rules, keep them honest.

Feeling this today, feels like everything continues to get worse. Trying to be more positive, and its hard.

Interesting take by Kenneth Reitz. Not quite sure how I feel about it anymore. It kinda hurts, but I’m not sure if code aesthetics matter as much as the product anymore. I cared when I was the one editing, but at this point I’m not doing a lot of edits by hand. Do these aesthetics affect the final products that users use, Not sure. AI makes me sad.

If agents make prime a bit faster, what does that mean for the rest of us mortals?

I’ve gotta agree with bob on this one, the first thing I did to my biggest brownfield project I wanted to use agents on BEFORE they did work was a hardened pre-commit.yaml, ci, hardened type checking and linting. SECOND get rid of bad inconsistent patterns, let them replicate consistency, force them to pass checks. Agents will follow all of your markdown suggestions most of the time, enough for you to become complacent if you let it. They are goal seeking, if you put them to a task you thought was possible that is not given your constraints, they will try to find a way given enough tokens. I dont see this ever changing, its one thing that makes them great, it just needs to be kept in check.

behind, yet positioned to completely dominate this race by hitting it with some sense. Making trends in what looks like longevity in the race that is not subsidising to simply get users, but to get by until they figure out how to 100x reduce the cost to a reasonable level. They feel like the guy sitting in the back with nothing big or flashy to say that is going to drop the hammer on their competition that overstretched itself taking on too much debt because it was necessary to change the game. There might be something to having a mix of hipsters, boomers, and luddites all trying to balance each other out.

5 star video, if you are going to watch one video to understand how harnesses and agents work, this is it. This really had my gears spinning on what tools do for agents and how big of a difference they make in their ability to manage context efficiently and accurately create changes. It’s crazy how good bash works, and that gives the agents the ability to do just about everything, but it could be better.

One of the biggest scientific achievement of our lifetime happened this week. I will forever remember sitting in a Culvers in between theater builds looking through these photos as they came live, looking at them in awe.

One of the most famous images from the shoot “Setting Earth”

What an amazing set of photos created by the Artemis II crew accompanying a fantastic breakdown by Hank Green.

I like this one, as its probably one of the ones not shred a ton

Whole gallery is worth looking at https://www.nasa.gov/gallery/lunar-flyby/

A really interesting long form interview with @simonwillison.net. If you follow him closely most of it is probably not new, but I found some interesting nuggets.

Simon is writing most of his code from his phone these days using anthropic hosted platform. He mentioned that a lot of security risks go away when you don’t put secrets on the platform and you let them take the risk of running ai written code with ai chosen supply chain.

He talked about the Pelican Riding a Bike benchmark for quite awhile. He was surprised at how well of a proxy it is for how capable a model is at just about everything. He also said that when he runs the benchmark he also runs half a dozen others that he’s never talked about so that He could see if they were to train a model specific to his benchmark he could catch them, but it seems they had caught on and if they were they seem that they would already be doing it on all of his others anyways.

TDD is incredibly boring for humans, it strips so much creativity and joy from the process. Who cares if agents are bored they do better when doing TDD.

THIS is the future of homelab, excited to see someone who knows so much more about hardware than I do get excited about this.

Is Glasswing the next inflection point

Absolutely sick texture app from cnc kitchen. Like him I’ve spent a bunch of time attempting and failing to learn blender, I’m so glad someone else vibe coded out such a good app that can just add texture to stls with basic masks and is the very basics of what you would want to add to 3d prints to make them interesting, I’m excited to use this for some real projects.

Bush on tiny desk. Iconic band on an iconic platform. Will be re-listening to this several times.

smassh is the coolest monkeytype tui clone, its impressively accurate. Easy to install and run, all the same themes appear to be there and everything. maybe a good way to get a few reps in while agents are running these days.

I need to go back and brush up on my skills I’m down a good 20wpm from what I should be doing.

I’ve been thinking about this for awhile and Daniel makes some great arguments here. Interestingly keeping inference cheap removes the incentives to make our tools better, help us choose the right model, lean on local models, open weight models. The frontier models are so affordable through subsidized subscription models why would you deal with anything less intelligent at this point. The tooling we use is not optimized for it, and why should it be.

emacs config so bad he launch obsidian, YIKES! grantid I’m using obsidian currently on my phone, not for this post, but for journal entries while I’m away from my desk. Use this as a reminder that you can swim through murky waters with your dotfiles for awhile, but occasionally its good to do a clean up, pin it, put em in a docker image, have a good fallback to go to if shit really hits the fan. Iv’e been using https://github.com/waylonwalker/nvim-manager as part of my strategy for awhile now.

uv adds dependency cooldowns via #16814. Well needed feature in todays world, far from a guarantee, but its something.

2026, finding the balance between fixed bugs and zero days. There is very unlikely ever a reason you need to be running bleeding edge packages in prod most package managers now support cool downs.

Everyone look away, nothing to see here.

Anthropic safewords are the talk of the town today.

webdev twitter is blowing up with implementations of pretext text calculations. The examples are absolutely fun and ridiculous.

The claude code source code leaked today and the tweets are great, maybe twitter is back.

Did you know you can replace the spinning verbs in Claude Code. I’m having fun with it.

I’m about to be pi pilled.

We f&#ing said @pype.dev, well f&#ing said. I think a lot of us are feeling this, we’ve pitched our brain into a bucket and we are no longer stretching it in the same way. We still work in similar ways of old, with new ways of turning off and saying yes a bunch of times. the best thing I can hope for is that as things get better we have fewer yes loops, and more architectural design debates and deep thoughts. But I fear deep thoughts are gone to the way of “research the leading 10 frameworks and pick the best one for this project.” and letting the clankers do the deep thinking. Its signing us up for a weird distopia.

I think a lot of us wish we could undo what has happened and go back to actually understanding what we are doing, but the world has changed, and if you are building average shit, like the average person, using models trained on average people doing average shit you cant keep up anymore.

I’m in step with @pype.dev here, I really want beads to work for me, but my systems for infra/platform work are all over the place, not one repo. I’m considering trying the BEADS_DIR env var but idk if it fits my workflow. For now, similar to @pype.dev, I am rocking my own home vibed solution that I’ve intentionally put little effort in and its working great and I expect it to be broken and not working with the latest harnesses and models within a few months anyways, cause there is no predicting this train.

oof, outage on the homelab during vacation, brutal. I can think of a couple of similar solutions to what @pype.dev has done to tailscale in, but I’m not sure that I could do this remotely. On one hand I’m so glad that cloudflared just takes care of certs on the other hand this really brings a gap in my understanding of what the heck I would do if it were broken.

An untested DR plan is not a DR plan.

An untested backup does not exist.

Vibe coding is going so far into the news sphere now that Adam Savage even weighs in with perspectives from someone who has built a life around building things with his hands, keeping up with new making techniques, discovering old techniques as they combine with new. He talks about 3d printing reviving his love of the pantograph as one automation technique eases the most difficult part of another.

This is a fantastic progression through kuberentes concepts. From running a pod, to making it resiliant, holding secrets, accepting traffic, and autoscaling.

I love the level of thought that Jim has put into these changes and making sure that urls don’t change. I’ve got a big change in flight to my main site and this is one of the reasons that I’ve been sitting on it so long. I want to make sure urls arent broken, redirects work as they should, and there are no 404’s from existing urls. Currently the new version only exists on a separate deployement https://go.waylonwalker.com/

I also added the ability to “shuffle” between posts. This is mostly for myself. I like to randomly jump through notes I’ve published in the past for reoccurring inspiration

Love this idea and have it on my new site already as well, and have really enjoyed using it by pressing it a dozen or so times over the course of a few sessions. It highlights that I have too many posts like stars and thoughts and I should do some weighting to main posts. mine is at https://go.waylonwalker.com/random/

Does anyone think fast-code will continue to pay the same salary? The answer isn’t to switch your brain off during your McCode shift and write a poem after work. Your job will be replaced by a Banglasdeshi slop-shop if AI improves (which is inevitable, apparently). Possibly the same sweatshop that loomed my £3 T-shirt. The Luddites didn’t accept their fate so easily.

David has some good points here, but I’m feeling the opposite direction a bit. Execs have always liked keeping the PM’s and the people steering the ship close by and were willing to farm out more and more grunt work. It feels like we are in a weird phase where there used to be a big group of people paid to write code. A few of them are exceptionally good at it and will remain. There will be a need for these people everywhere. Somehow we still need people hand editing assembly code optimizations, fortran, and cobol today. Those industries largely moved on, but a few great ones remain. I think this fast-code slop factory is going to be a short forgotten time in history, but no one yet knows what’s next. We are all waiting to find out. Just with anything there is still value in doing it by hand and...

Great gusto here from someone looking to fill landfills less. Get more use from what they paid for. Dodge some tough times in the hardware industry. I’m going to argue that the 10 year computer is not one bit crazy right now. No idea what the future entails, if local llms get good enough to really get so useful they feel required this could easily change. One issue I had with the post as they are looking to get a machine for the next 10 years is they were so focused on themself that they missed the point. They were so focused on buying something that would work for them for 10 years that they bought something brand new rather than thinking about the bigger issue of how do we get hardware to last 10+ years. Some factor of this involves giving our devices a second life. Two things went wrong here. First it appears they they have a perfectly good imac with a broken screen. I know nothing about apple/imac, assuming that the screen is toast and unrepairable, I know you can ssh into a mac this feels like good potential for server hardware. Next they purchased a brand new mac mini. Hardware has been good for a long time, there is no need to buy new right now, especially now. I haven’t bought a new machine in years and most of my hardware is second hand cobbled together stuff, and has no issues. I’ve got one machine thats 16 years old, 2 machines at 9 years, one at 8 years. To get here they need to be repairable, designed to last, and probably no run windows as they will release something that renders them too slow or require new hardware for security that wont work.

Very interesting takes from @thdxr in this interview. A lot has been hashed out by others all over the place, but a hot take here is that code quality is higher than ever right now. Codebases are becoming more consistent than ever. If you are not starting with a good consistent base from the start you are poising your context and doomed to fail and have all the common failures of ai written code. He still reads almost every PR, and will read all of the code eventually. There are a few cases where reading the PR is not worthwhile only when its low stakes, knows that good patterns have been established and followed. He argues that someone needs to be the expert of the code and of the product still and fears that too many people not looking at prs will fail companies.

Kids are leaving the party early, not drinking, cant watch netflix without the laptop open. They are leaving the party early to check on their agents. I get it, that feeling that you need to eek out one more prompt, keep your agents running. if they arent running what are you even doing. If not you 6 others are ready to pass you up. The timeline to be first has shrunk to nothing but unachievable.

😂 Should I be concerned that My 12yo installed Arch BTW on his own?

It’s wild how much of a hit Google took from killing reader, almost any time I hear about killedbygoogle, reader is the top of the list. Its the thing that we all remember being really good and the incumbants just did not match up. Somehow we are here 13 years later still bitching about it, despite it only having a 6 year run. You should probably get an rss reader, and follow some incredible people that make feeds. Most sites that produce content have the ability to subscribe over rss. Unlike @pluralistic.net, I dont read in my reader. My reader is just a list of links out to the web and I typically read it how the author intended on their site. I nod a long to Cory’s enshitified internet just as much as the next guy, I love text based interfaces, I despise the bloat that js has brought on. But I don’t believe all js is bad, I don’t turn it off, even though he has me questioning this now. News sites kinda suck, we can agree there, but its rare that a small indie web creator has fully enshitified their site with js. I don’t buy that. Sub to the feeds.

Sent Justin my list https://go.waylonwalker.com/blogroll, will soon be on the main site, but right now its only on the go subdomain. I’ve long had reader.waylonwalker.com, but thats soon going to be wrapped into the main site as well at /reader.

I’m interested to see what good stuff Justin gets and if you have any good ones to share reply.

One of the well worded shitty messages I’ve seen, good severance, help, timeline to cut off coms.

we’re not making this decision because we’re in trouble. our business is strong. gross profit continues to grow, we continue to serve more and more customers, and profitability is improving. but something has changed. we’re already seeing that the intelligence tools we’re creating and using, paired with smaller and flatter teams, are enabling a new way of working which fundamentally changes what it means to build and run a company. and that’s accelerating rapidly.

Much better than the get rid of people cause AI can do the work. Honestly I feel this though. I was just talking with some colleages how do we divvy work in the age of agents without just constantly walking on each other. If each of us is now an architect who is managing teams of junior agents under us it feels MUCH different than before.

I’m far from working in a large software org like this and I’m feeling it. I only imagine that it gets worse the more people that have to orchestrate around each other.

...

This was the inspiration for the next update in dropper that became a full clip editor. The one that I’ve long wanted, but forgotten about. It’s going to include this cropper, resize, image extractor, and trimmer.

Learned about this one from the @stipete interview @scotthanselman did on YouTube. This is proof that the internet is alive. It’s such web 1.0 nostalgia to see that people can just build things! Did you know that you can literally just build things and make them exist? You don’t need users, You don’t need a big platform, you can just make something into existance. It seems like something we have forgotten through web 2.0 where everything as become 4 major apps all linking to each other and trying to hoard all of the attention. Scroll through tehre are some really cool apps, probably nothing that has the polish you want, or is going to change your world. What these apps have more than anything you’ve probably used in the recent years, is inspiration. Its xyz, but the way I wanted, or with my little twist. And no one else has to like it but me because I’m the user.

I saw this in @cassido’s newsletter this week and had to give it a run. I despise that there is no dark mode and it insists on burning my retinas 😤. But really this is an absolute beate of a web based markdown editor, I love the command mode to press slash and it just pops out in this whimsical animation ready for me to pick what I want.

I had no idea there were such things as “reply guy” as a service. I can see this as a really genuine thing where brands want to genuinely engage with their communities, quickly being taken over by slop bros to ruin everything.

Important things to remember in the age of cheap code. More code, not always more better. More code mean, more risk, more maintenance, harder to change.

THIS, THIS is how most people are feeling about AI right now. Theres lots of “oh ai bad”, “but ai help”, “but ai company sleezy”. Cassidy did a fantastic job summarizing how most of us are feeling. Ending with well at the end of the day, I can’t do anything about the bad, the best thing I can do is learn how to embrace the good cause it aint going away any time soon.

This is a wild way to build prototype pcb’s, so cool and creative.

...

Had 10 minutes to play with the new session updates this afternoon and it feels so much smoother. I can definitely feel it even as a casual user.

There are so many config files right now, glad to see some standards coming in around Agents.md, but so much is still specialized to a whole host of tools that have not been standardized on yet.

This is an abolute banger of a game on itch. It nails the nes aesthetic while keeping true to the modern silksong movements. You can play through the first boss Moss Mother, and where you start the first ascend into Bone Bottom. I was in shock when I discovered the little climb effect hornet does when you just cant quite make a jump, the hold jump for height is on point. Her downstrike with the hunters crest is perfect.