Zach Silveira

Here's a quick look at the complete MCP server I setup, using the new Auth spec from May. Added it to claude.ai and it fully works with the new streamable http spec too! #ai #mcp #LLMs #claudecode

Streaming my vitals to AI was a fun experiment zach.codes/p/streaming-my…

@luisrudge also are you using mac trackpad there, i need to have ai debug this for sure if you are lol

@zachcodes this is what I see on Ghostty

anyone know if copy/ paste in opencode will ever get on par with claude code?

Am I the only one who 99% of the time uses Claude or opencode or codex on manually accept edits? I get the review in as I go and quickly voice to text to tweak. Running to end then finding problems is more annoying

You've never needed nextjs or a frontend framework Use script type module and use bun build exported to a storage bucket. Oo you need fancy "static pregeneration" OK have Claude spend 35s to make a script that loops your pages and renders them to HTML. Plain react can go far

@luisrudge Scroll_speed in opencode

@luisrudge When I first got it with I term I didn't like the default speed of 3 so I set it to one. And I have a super high trackpad sensitivity. So I wonder if their app doesn't handle that well. No other tui has this issue its weird

@luisrudge I wouldn't MIMD it if the scroll worked correctly. Moving my mouse's slightly makes it go all crazy

@zachcodes never saw it glitching, but yeah the auto copy thing felt weird on the first day but my reality is that every time I selected something I wanted to copy it and now I miss this in other TUIs haha

@luisrudge I already used it in native terminal ghostty and iterm2 so it's not my terminal.

@zachcodes wdym? what's the difference? you can copy text and images what else do you want 😅

As soon as I switched back to ollama cloud as the provider. The exact same task one shotted with no issue. The opencode team should be transparent about where the models are coming from and why they are performing badly or heavily quantized

I use Claude and opencode and openclaw a lot now. Sounds crazy but I enjoy testing out all the models. Its sad that opencode go has a messed up glm5 provider. Tried it out yesterday and it was atrocious

openai and anthropic will go to 0 in a few years when m5,6,7 ultra's are able to prompt process incredibly fast. qwen 3.5 122b a10b and qwen3-coder-next are already usable on device with a lot of ram

🚀 Introducing the Qwen 3.5 Medium Model Series Qwen3.5-Flash · Qwen3.5-35B-A3B · Qwen3.5-122B-A10B · Qwen3.5-27B ✨ More intelligence, less compute. • Qwen3.5-35B-A3B now surpasses Qwen3-235B-A22B-2507 and Qwen3-VL-235B-A22B — a reminder that better architecture, data quality, and RL can move intelligence forward, not just bigger parameter counts. • Qwen3.5-122B-A10B and 27B continue narrowing the gap between medium-sized and frontier models — especially in more complex agent scenarios. • Qwen3.5-Flash is the hosted production version aligned with 35B-A3B, featuring: – 1M context length by default – Official built-in tools 🔗 Hugging Face: huggingface.co/collections/Qw… 🔗 ModelScope: modelscope.cn/collections/Qw… 🔗 Qwen3.5-Flash API: modelstudio.console.alibabacloud.com/ap-southeast-1… Try in Qwen Chat 👇 Flash: chat.qwen.ai/?models=qwen3.… 27B: chat.qwen.ai/?models=qwen3.… 35B-A3B: chat.qwen.ai/?models=qwen3.… 122B-A10B: chat.qwen.ai/?models=qwen3.… Would love to hear what you build with it.

Qwen3.5-35B-A3B is now available in LM Studio! This model outperforms previous Qwen models that are more than 6x its size 🤯🚀 Requires about ~21GB to run locally. lmstudio.ai/models/qwen/qw…

@lmstudio Is the mlx coming soon?

Why do MCP servers act like authentication was just built this year on the web? I shouldn't need to re-auth an mcp server every single day.... set a longer session lifetime geez

@lmstudio any word on support for glm4_moe_lite

Every time I try to give opencode another shot Some weird thing like this happens. Turns out it's expected to list models that don't even exist when you add @lmstudio github.com/sst/opencode/i…

@jlongster Split that into 10-15 posts if you want engagement and visibility to each key part.

I'm brewing a really really big post on frontend stuff like 10,000 words big with deep tech demos should I break it up and release it in parts? or just one big thing?