krschacht

Qwen 3.8 is surprisingly usable for a local model, especially inside the Claude Code TUI

In the last 18 months I tried a Framework twice and both times ended up returning it. I was running Arch both times and had too many low level issues.

I couldn’t get hibernation or sleep to work reliably. And about once a week I’d get a random freeze or crash that required me to reboot and lose all the windows I had open. I spent dozens of hours with Claude chasing things down, disabling various power management features, trying different kernels.

I really appreciate how much Apple computers just work. I’ve since invested heavily in Karabiner, Aerospace, Superkey, and a few other utilities to get close to the level of customization I had in hyprland. I still miss the polish I used to have, but I can close my laptop lid, walk out the door, and 100% trust I’ll open the lid and resume work. That counts for a lot.

I’m keeping an eye on Omarchy and Framework to see if they eventually solve all issues. Maybe in a couple years I’ll try again…

Which god are you asking about? People have come up with so many different ones. Do they all count?

I’ve been starting companies my whole career. My first real one was a software dev shop while in college, I sold it my senior year and dropped out. It wasn’t much of a financial success but it was more fun than typical college job. So sure, a success by my standards but not by most others.

My next one paid me a salary, but I had a falling out with my cofounder and sold my shares for very little to get away. Success? I felt like it, again, maybe externally.

Two duds after that, one I raised money for so I got paid a salary and I sold it to recoup most of investors money.

The one after that was a big hit: we grew to 50 employees, 8 figures in revenue and 9 figure exit.

I like to say: if I could find the perfect job, it’s much easier to work for someone else than start my own thing. But I have specific interests I want to chase so creating a company is my way to create the “perfect” job for myself. If you take this approach, it’s much more likely to be successful in your own eyes.

At the end of this article it states, "Our tests gave models the vulnerable function directly, often with contextual hints (e.g., "consider wraparound behavior"). A real autonomous discovery pipeline starts from a full codebase with no hints." I'm not a cybersecurity expert, but isn't 80% of the challenge finding where the exploit lives in the code!?

That really undermines the author's claims. This article feels dishonest in it's claim that "small, cheap, open-weights models ... recovered much of the same analysis."

Dang, that would be unfortunate if this is driven by ads.

I think I see the problem… and a possible solution.

I think the main problem with attempting to document this is that the system would not be running off of it. Your infrastructure document is automatically read and drives the deploy (or whatever). But if you want to make a change to a human’s responsibilities, you don’t get the simplicity of updating your organization documentation and clicking “execute.” So this new documentation you propose would always be lagging documentation rather than the actual driver of organizational behavior.

But! What if it was? What if all the managers in an organization were AI systems? They would read diff in the org chart and it initiated the communication to the respective human employees.

I could imagine testing this in a coffee-shop level business right now in which the LLM is probably capable of all the strategy and management decisions needed to effectively run it, operating within the constraints of policies and procedures all cleanly laid out in documentation.

For something like tests, where I have very specific opinions on how I want them written, I have a simple doc (tests.md) and I’ll regularly tag Claude with it.

Claude writes a bunch of new code and I’ll tell it, “Before I review this code, make sure all tests adhere to the guidance of @tests.md” (you can probably make this a slash command too)

I find that if I put these instructions in the system prompt, far down in a conversation that’s used lots of the context window, they will only loosely be followed. But when I tag it in like this, Claude will strongly and thoughtfully follow the guidance and examples I’ve written up about how I want my tests.

antirez — how do you reliably get Claude to re-read the file after compaction? It's easy to let Claude run for awhile, it compacts and starts getting much worse after compaction, and I don't always catch the moment of compaction to be able to tell it to re-read the notes file.

Run your own server for GitHub Actions. There is a simple library they have you install so your runner gets registered with your repo. Then you can SSH in whenever a job fails. This lets you fully inspect the state, and to execute one-off commands to test theories. It’s a much faster way to iterate.

Here are two of mine:

Volumetric displays: https://youtu.be/na7pvihXhYs?si=cIWIk2yrv-WVbe4x

Physically adaptive desktop: https://tangible.media.mit.edu/project/transform-as-dynamic-...

I'm eager to learn about ones I've never seen!

I don’t lock down my kids computer use. I know risks exist, but I think their unrestricted access to computers and the internet is far more beneficial than harmful.

I know I’m highly unusual amongst my friends. I’ve also found it odd that the more knowledgeable someone is about tech, the more scared they are of their kids using the internet.

But just like riding a bike and swimming in a pool are extremely dangerous, yet I encourage my kids to do both of these things and instead just educate them about risks. Similarly, I think the benefit-vs-risk of the internet is FAR better than a bike & pool, so I just educate them.

(1) and (2) are good points. Particularly 2 because movies may intentionally add steps / slow things down so that a viewer can follow along but this would be at odds to daily use.

However, I still think there's something to be said for movies attempting to build UIs that have a strong aesthetic and elicit an emotional response, whereas production apps feel so flat and boring, in comparison.

I still wonder why we aren't seeing people try to push the envelope stylistically to "wow" users.

My assumption is a bit different: the UIs in science fiction are intended to communicate information, now typically that's to advance the storyline but there's a lot of overlap with real apps. Maybe more importantly, UIs in movies are elicit a feeling. Maybe it's a shallow feeling of "this is cool!" but to me that's where it seems like production apps mostly give up. "It works, let's move on..." seems to be the bar in most cases rather than "let's wow users!"

This might be a clearer articulation of what I'm trying to get at with my question...

I've been keeping an eye on the SDKs for Meta glasses and Even Realities, but they don't yet support much access.

What does it say about moving to cash now? :)

I find most human agents can only produce high quality tests if you give them detailed guidance and good starting examples. :)

Since you are convinced you’re using the tools to their full potential, the quality problem you experience is 100% the tools fault. This means there is no possible change in your own behavior that would yield better results. This is one of those beliefs that is self fulfilling.

I’ve found it much more useful in life to always assume I’m not doing something to its full potential.

Yes, most days I’m 2x as productive. I’m using Claude Code to produce extremely high quality code that closely follows my coding standards and the architecture of my app.

You aren’t entertaining the possibility that some experienced engineerings are using these tools to produce incredibly high quality code, while still massively increasing productivity. With good prompting and “vibe engineering” practices, I can assure you: the code I get Claude Code to produce is top notch.

Simon, I think this is a good distinction. Another possible term could be: “agent engineering management” or simply “agent managing.”

I am deep in this and one important way in which managing agents is different than managing people is that micro-managing can be your friend. With human engineering colleagues, you need to allow for a healthy degree of “that’s now how I would have written the code, but it’s a reasonable way to write it.” But if my agent writes the test file in the exact same way I do, I can both review and maintain the code more easily.

I have a bunch of short markdown doc files in which I give very specific instructions for how I like code organized: much stricter than I would ever do for a colleague. I’ll tell the agent, “now add tests to this model and follow @unit_tests.md” This file specifies exactly how I like tests named, what order I like them written in the file, etc. I have docs for: models.md, controllers.md, concerns.md, and fixtures.md.

The cost of developing software is quickly dropping thanks to these models, and the demand for software is about to go way up because of this. LLMs will just be power tools to software builders. Learn to pop up a level.

I can type much faster than I can mouse. And for apps like IDEs, there is great keyboard support built into them. But take an everyday task like clicking the unsubscribe link in an email I’ve received; there are too many situations where keyboard navigation doesn’t work well.

Through a combination of two apps on my Mac, finally I can quickly navigate any programs with the keyboard.

And this just landed too: https://pragprog.com/titles/jmnative/hotwire-native-for-rail...

I’ve done one app with Hotwire Native and it’s a pretty interesting solution. However, just like a truly complex and dynamic web UI can reach a level of polish with React that is hard with Hotwire, a truly complex and dynamic mobile UI can reach a level of polish with Swift/Kotlin that is truly hard with Hotwire. It makes the vast majority of experiences much faster to build, but certain complex experiences are hard to get polished.

However, Hotwire (web & native) can get you almost the full way there and you can just drop a React/Swift/Kotlin view in for parts of the app where you need it.

It’s really a different mindset shift. In react, you think about components — updating components and replacing one component with a new component. But in hotwire, you think about pages. First implement everything as full page transitions. Only after you get all your functionality working with full page transitions, then you do a pass back through it and ask: how can I minimize the amount that changed between the transition from this page to that page? “Oh, just wrap this part in a turbo frame or have this one controller action reply with a turbo stream in this one case.”

I don’t know if that’s helpful, but realizing that I needed to shift from thinking about components to pages was the a-ha when Hotwire all started making sense.

Render is another good option. I too prefer Fly for my toy apps, but it has a little bit more of a learning curve than Render.

I too find Claude for Rails to be really helpful, except for some of the newer features in Rails 8 for which there is a lot less documentation. I use Claude within Cursor and it has the ability to at-mention documentation so any time I run into this I just follow up with “Can you please double check the @rails8 docs and try again.” (likewise for @stimulus and @hotwire docs)

I agree this is something missing. I wish the framework had it. I bookmarked this to try out soon: https://github.com/igorkasyanchuk/rails_db

I know there are a few other projects like this which I’ve seen over the years, but I’ve yet to truly investigate any.

I find this fascinating as well. And I think it’s because part of the ruby & rails cultures are to deliberate cultivate delightful touches in the language & framework. This creates a positive feedback loop that has kept the “honeymoon phase” alive much longer (at least for me) than many other technologies I’ve fallen in love with.

Ruby has Sorbet if you want to add typing. And better concurrency constructs for Ruby are in the final stages of being backed with Fibers. For example, Falcon is the new Ruby web server that’s built with Fibers. It’s not quite ready to replace Puma but Fibers are coming along.