Dagens Vibes — 19. juli 2026

Qwen@Alibaba_Qwen

Qwen3.8 is launching and going open-weight soon!🌐 With a massive 2.4T parameters, this model is continuously evolving. We believe it’s one of the most powerful model available today, compatible to leading frontier AI models , second only to Fable 5. You don't have to wait to test it. Just now, the Qwen3.8-Max-Preview made its debut on Alibaba’s Token Plan, Qoder, and QoderWork. Be among the very first to try it out. Can't wait to hear what you build. Stay tuned! 🚀  Token Plan international：https://t.co/YRvcGdB9Bv China：https://t.co/PKMUNwUuRp

David Bau@davidbau

Is it possible to write 100,000 lines of code well, if you do not read it? Let's go Hunting Zombies! https://t.co/laLKgrDGNI In this post I dive into the code of two AI agent contestants in the Teleport coding challenge to learn their secrets. Very fun. And also instructive. https://t.co/OiMWhvbEDK

Ryan Lopopolo@_lopopolo

I distilled myself and my work to twelve theses of harness engineering. This represents the last year of my work. This is the practice and technique. Go nuts fam. https://t.co/7ZqSMIFN9H https://t.co/rzMP5tQkno

Taelin@VictorTaelin

I think I finally figured out how to use AI at scale of course, the fact Fable is good is part of it. but I also changed how I work, and it all comes down to one key realization: you don't need to audit the code, but you NEED to audit the *choices* it made. if you just do that, things will work out, and you'll never lose a codebase to chaos. with Fable at least, the following seems to hold: if I give it a good decision: Fable implements it PERFECTLY if I let it decide instead: Fable may make some bad choices that's how I see Fable: as a perfect execution machine capable of converting good decisions into good codebases, no matter how large. given a concrete plan, it lands its implementation. but when anything is underspecified, it can, and will, make bad choices. that's what you must audit. "while working on this, which choices did you make that you're not confident of? list all." then, you just review that. not the git diff, not 1000's of lines of code. just the choices it made along the way. below is a fresh example. overnight, I asked Fable to fix an issue related to MatMul parallelizing worse than expected. it tracked the culprit with perfection, and landed a solution that DID work. but the solution was not general. it just doubled a buffer, which coincidently fixed the program at hands, but the underlying issue was still present. when it completed the job, it declared success. if I just merged it blindly, the issue would still be dormant. that's the main mistake one can do with AI. instead, I asked it to spell out all decisions it made, spotted the bad one, corrected its course, and now the codebase is clean, correct and the issue is gone for good I really think that if you do that religiously - i.e., NEVER merge without this "which decisions you made?" audit - you can go VERY far without ever reading a single line of code. at least on Bend, this is working incredibly well. despite heavy use of AI to implement an ungodly amount of features I could never dream of, the codebase is still in a superb state, with no signs of degradation fresh example below ↓

Kimi Developers@KimiDevs

When your application needs a large number of tools, declaring all of them up front in the top-level tools field of every request leads to Tool Definition Bloat: every request carries the descriptions and parameter schemas of all tools, driving up token usage, and the more candidate tools there are, the more likely the model picks the wrong tool or constructs invalid call arguments.

dax@thdxr

used a trick @jlongster came up with agents can control browsers but you can also ask it to record network requests into a HAR file then it can derive a client for any website which is more efficient than browser controlling it every time made it build a quick uber eats cli https://t.co/xWNOsMRMoJ

David Crawshaw@davidcrawshaw

A weekend project in a single prompt. I wanted a little button to put down one end of the house that the kids could push to get my attention. Online I found the Atom S3 Lite for $18: it is a button on an ESP32 that attaches to Wifi. My office is littered with half-complete weekend projects involving embedded controllers, so I was not hopeful this would work. But $18 was not a huge commitment. By the time it arrived I was ready to write the project off. I have a talk to deliver for DevRelCon on Tuesday I need to work on, no time for a project like this. But then I remembered: at work we use the Pushover iOS app to send internal system notifications. It is easy to use, just a POST. And I remembered that the Flipper Zero can flash its firmware over a web browser. So I opened Shelley on @ssh_exe_dev, and typed in a single prompt. Ten minutes later, it pinged my watch and said it was ready. I went back to my Mac, opened the exe URL for the app, copied in my Pushover key and clicked "Install Firmware". It worked. I pressed the button on the little ESP32 device, and I got an iOS notification on my watch. I was amazed I could write firmware for a piece of hardware without installing a single program on my laptop. The entire toolchain was isolated to a VM. An entire weekend project to build a button for the kids was reduced to a single prompt.