Published

All published posts

2565 posts latest post 2026-07-13 simple view
Publishing rhythm
Jun 2026 | 27 posts

Tokens Just don't go as far as they used to

Not sure if this is simply the flavor of the month, or a shift in gpt5.4 being super subsidized on release and now that we have gpt5.4-mini-fast out they have shifted, but I'm burning through half of my $20 gippity sub in a day with hobby level use. Second week in a row its burning so fast.

Stow comes with a local and global ignore list that you can use to ignore certain files or directories.

If you put Perl regular expressions, one per line, in a .stow-local-ignore file within any top level package directory, in which case any file or directory within that package matching any of these regular expressions will be ignored. In the absence of this package-specific ignore list, Stow will instead use the contents of ~/.stow-global-ignore, if it exists. If neither the package-local or global ignore list exist, Stow will use its own built-in default ignore list, which serves as a useful example of the format of these ignore list files:

Example given from the docs

RCS
.+,v

CVS
\.\#.+       # CVS conflict files / emacs lock files
\.cvsignore

\.svn
_darcs
\.hg

\.git
\.gitignore
\.gitmodules

.+~          # emacs backup files
\#.*\#       # emacs autosave files

^/README.*
^/LICENSE.*
^/COPYING

Reference #

https://www.gnu.org/software/stow/manual/html_node/Types-And-Syntax-Of-Ignore-Lists.html

Ping 52

Is it just me or are the agents not behaving today?
"Am I Crazy?" [Wading Through AI - Episode 3] www.youtube.com
- 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?

Ping 50 A

I wrote code by hand today... I was out of tokens
A love letter to Pi | Lucas Meijer www.youtube.com
- 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 [1] 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. References: [1]: /html/
How Claude Code’s Creator Starts EVERY Project - YouTube www.youtube.com
- 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.
Write It First, Then Let AI Drive - Kenneth Reitz kennethreitz.org
Write It First, Then Let AI Drive There's a thing that happens when you start using AI coding tools seriously. You assume the best workflow is obvious: let AI generate the first draft, then... Kenneth Reitz · kennethreitz.org [1] 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. References: [1]: https://kennethreitz.org/essays/2026-04-12-write_it_first_then_let_ai_drive

Prove Yourself Agent

Ask your agents to prove their work. Include it in the initial prompt, not later.
I am slowly coming around to AI assisted programming. x.com
ThePrimeagen (@ThePrimeagen) on X I am slowly coming around to AI assisted programming. I am genuinely trying to codify every rule about programming that I have and using that + several stages to build out small changes. Not s… X (formerly Twitter) · x.com [1] If agents make prime a bit faster, what does that mean for the rest of us mortals? References: [1]: https://x.com/ThePrimeagen/status/2043861800819761382
AIs aren’t good rule followers x.com
Uncle Bob Martin (@unclebobmartin) on X @ThePrimeagen AIs aren’t good rule followers. The older the rule in the context window, the less priority it is given. So the best way to enforce the rules is with external tools that communicate... X (formerly Twitter) · x.com [1] 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. References: [1]: https://x.com/unclebobmartin/status/2044065822067282396
A quote from Steve Yegge simonwillison.net
Steve Yegge Steve Yegge: I was chatting with my buddy at Google, who's been a tech director there for about 20 years, about their AI adoption. Craziest convo I've had all year. … Simon Willison’s Weblog · simonwillison.net [1] 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. References: [1]: https://simonwillison.net/2026/Apr/13/steve-yegge/#atom-everything

An ai model created by Anthropic was announced as a closed preview on April 7, 2026 for critical security research and evaluation with its close partners with critical software such as operating systems and browsers. Anthropic claims that mythos is able to reason through so much more context that any model ever before. This enables it to find bugs that are 25 years old in the BSD, considered one of the most secure operating systems we have. Once it finds these zero day bugs never discovered before its able to use them together in malicious ways never expected. In ways the world is not ready for. At the time of writing these are claims without proof. It remains scary to know the potential this has and that there is only a few companies with this potential that will gatekeep who gets access.

What happens when the 0 days are exposed?

What's going to happen to all of our software when Anthropic Mythos finds all of the 0 day vulnerabilities? Will everything depending on the bugs break? Will it be possible to fix them cleanly? Will we all get pwnd when the bad actors get access to them before everything is patched? Will LTS Operating Systems Die?
How does Claude Code *actually* work? - YouTube www.youtube.com
- 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.
Clearing out Creige's Cellar for the Vintage Nectar.
Fighting the second Savage Beastfly in Far Fields
Artemis II Lunar Flyby www.nasa.gov
Artemis II Lunar Flyby - NASA The first flyby images of the Moon captured by NASA’s Artemis II astronauts during their historic test flight reveal regions of the Moon's far side, as well as an in-space solar eclipse. Released... NASA · nasa.gov [1] 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. [2] One of the most famous images from the shoot “Setting Earth” References: [1]: https://www.nasa.gov/gallery/lunar-flyby/ [2]: https://dropper.waylonwalker.com/file/9987010a-a448-472d-9c60-2831b61a1d3a.webp
Explaining the Most Important Artemis II Photos - YouTube www.youtube.com
- What an amazing set of photos created by the Artemis II crew accompanying a fantastic breakdown by Hank Green. [1] 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/ References: [1]: https://dropper.waylonwalker.com/file/0b53a4ed-924e-42b5-84f4-51c189f60801.webp