I have been disappointed with the relaunch of Fable 5 due to the default switching to Opus 4.8. Over the past year I have been using sporadically initially the GLM models from Z.AI within Factory. When Factory added Missions, it was a game changer for me and my process. I am currently testing an alternative that, so far, is working well for me. Here is the stack: 1. 1. Using ZCode as the harness. Z.ai confirmed that this is the best harness for GLM-5.2. 2. 2. I recreated Factory's Mission Skill. I have been super impressed with their Missions workflow. 3. 3. I have a Abacus.AI account that allows me to use their api for different models. This could be replaced with Openrouter. 4. Here is the sauce: In ZCode I added additional custom models (opus-4-8 and gpt-5.5). In the Mission Skill I have three agents: orchestrator (opus-4-8), worker (glm-5.2) and validator (gpt-5.5). The mission skill builds the detailed long running plans in phases and standsup a Mission Control page to track progress. This has been working well for me and giving me great results. The reason why I am all in on ZCode is that I bought a yearly plan last fall and have a ton compute to use monthly. And since the model is now so much better and closer to the frontier models, I finally think it's time for me to fully test it and give it the best harness and structure to be successful. I added a few screenshots. Thanks to @Ray Fernando for the early Factory Droid and GLM exposure last year. 1.

Fable 5 is back you guys and it's included in the subscription until the 7th of July.. After that you have to pay usage credits to use it.

Anyone who uses Sonnet for simple tasks in a workflow just got a massive intelligence boost and a price drop for those testing, tools calling and debugging jobs. Big brain work is still an Opus 4.8/ChatGPT 5.5 task (and hopefully Fable 5 and ChatGPT 5.6 soon) but if you are into the multi agent workflow and need a smart, cheap minion to leave more tokens/$ for your larger models then this is a great day for the coding world I think. There will be a lot of hissing and booing online because its not Fable 5 but I think they are missing where the value has been added. A rising tide lifts all boats and this is definitely raising the baseline. https://www.anthropic.com/news/claude-sonnet-5

So I like to do some creative development and mainly develop QA apps for testing. Last week I was working on an local-first desktop app for anonymizing CSV files. It detects sensitive columns, lets you preview them how they would be anonymized based on the settings you use and you can output the new csv file. So the data can be shared with an LLM for explaining a certain data shape to help with things like data validation for example :) So I been doing a lot of development using Rust and now thought, lets makes this one in electron. When the final build was in it was about 300 mb and I was like this is huge. I then tried electrobun and got it down to something like 100mb. Now I'm back on my preferred tech stack I suppose when creating desktop apps and that is Rust + Tauri with a React/Typescript/Vite frontend. This app now is lightweight and performant and just 23,8 mb in size after installation and has the same rich functionality. I'm curious if you guys have any preferred tech stacks you use and why. I'm like lightweight apps that don't take that much space if possible.

I was watching a YouTube video by Matt Pocock yesterday where he talked about the skills he has developed. One that stood out to me was the Teach skill. You can use it within your project to help you learn new things. It basically asks what you want to learn and then guides you through it. I thought it might be interesting to share :) I think there is some truth in the idea that upskilling yourself can also multiply what you’re able to achieve with AI.