GosuCoder
@GosuCoder
Programmer that Loves to Share Things on YouTube especially about AI and new technology! Building http://raleon.io
Claude Code now has the ability to create custom sub agents. Use /agents and follow the steps. This unlocks so much, I’ve created a couple already and it’s working great. Big feature request is to be able to assign opus or sonnet to the sub agent.
I can't tell you how hyped I am about Qwen3 Coder, I spent the entire day solely coding with it, and it was actually enjoyable. Reminds me of the days when DeepSeek V3 first came out. It works amazingly in RooCode, you just have to set temp to 0.7. Video coming out in the…
Meet my pet Fluffly, this was built using the new Qwen3 Coder model in RooCode (where it works great). Should have a full review with evals out tomorrow morning! It works in RooCode exceptionally well It works in opencode fairly well Debating if I should test out Qwen Code...

Here's a quick gif what I've been building. Behind the scenes is a very complicated agentic system: 1. We use a combination of models 4o, Claude 3.7, Claude 4, 4o-mini, and Gemini 2.5 pro. 2. Machine Learning models that automatically train based on a particular stores data.…
This is what happens when 1 person has the power of 5 specialists. Data analyst + strategist + copywriter + designer + email expert. All with your Klaviyo, Shopify and brand data. All automated in one agent. Prompt: "Perform an analysis of last month's campaigns and flows.…
You'll never guess, but Claude is down again... It must be painful for the Anthropic team to deal with this constantly. At least its Frolicking



Seeing an enormous amount of people saying Claude 4 has degraded significantly. I don't think its been as terrible for me yet, but what I have noticed. What I've noticed very subjectively at the moment: 1. Shortcuts that didn't feel like they happened before. Example I can't fix…

AI coding works better when you know the inner workings of what you are building… frameworks + language. I’m a noob at Rust for example and I find it painful to really guide AI effectively when working with Rust. While Node,C++,Java etc I feel like it gives me super powers. How…
Thinking about how we measure the effectiveness AI at coding beyond what I'm doing already. Several things have become very clear to me. 1. The harness the models run in along with the prompts matter a lot. Model/Agent pairing is what we need to test. 2. Updates appear to happen…
This AI cycle is so weird Elon worries that AI is an existential threat to humanity. People that don’t code say AI will replace all programmers 18 months ago already. Programmers know that AI still needs a lot of human intervention to be useful. Companies have pivoted…
I was wondering when this would happen! Next prediction for me is there will be a hybrid or non reasoning coding focused model. Because if I was leading those teams I’d be laser focused on winning developers.
Gemini Code Assist now shares the same technology with Gemini CLI! In VS Code, place any prompt into the chat window using agent mode, and Code Assist will work to write tests, fix errors, build out features, or migrate your code → goo.gle/4o5eEp4