Thursday, 31st July 2025
Ollama’s new app (via) Ollama has been one of my favorite ways to run local models for a while - it makes it really easy to download models, and it's smart about keeping them resident in memory while they are being used and then cleaning them out after they stop receiving traffic.
The one missing feature to date has been an interface: Ollama has been exclusively command-line, which is fine for the CLI literate among us and not much use for everyone else.
They've finally fixed that! The new app's interface is accessible from the existing system tray menu and lets you chat with any of your installed models. Vision models can accept images through the new interface as well.
Trying out Qwen3 Coder Flash using LM Studio and Open WebUI and LLM
Qwen just released their sixth model(!) of this July called Qwen3-Coder-30B-A3B-Instruct—listed as Qwen3-Coder-Flash in their chat.qwen.ai interface.
[... 1,390 words]Here are a few more model releases from today, to round out a very busy July:
- Cohere released Command A Vision, their first multi-modal (image input) LLM. Like their others it's open weights under Creative Commons Attribution Non-Commercial, so you need to license it (or use their paid API) if you want to use it commercially.
- San Francisco AI startup Deep Cogito released four open weights hybrid reasoning models, cogito-v2-preview-deepseek-671B-MoE, cogito-v2-preview-llama-405B, cogito-v2-preview-llama-109B-MoE and cogito-v2-preview-llama-70B. These follow their v1 preview models in April at smaller 3B, 8B, 14B, 32B and 70B sizes. It looks like their unique contribution here is "distilling inference-time reasoning back into the model’s parameters" - demonstrating a form of self-improvement. I haven't tried any of their models myself yet.
- Mistral released Codestral 25.08, an update to their Codestral model which is specialized for fill-in‑the‑middle autocomplete as seen in text editors like VS Code, Zed and Cursor.
- And an anonymous stealth preview model called Horizon Alpha running on OpenRouter was released yesterday and is attracting a lot of attention.
The old timers who built the early web are coding with AI like it's 1995.
Think about it: They gave blockchain the sniff test and walked away. Ignored crypto (and yeah, we're not rich now). NFTs got a collective eye roll.
But AI? Different story. The same folks who hand-coded HTML while listening to dial-up modems sing are now vibe-coding with the kids. Building things. Breaking things. Giddy about it.
We Gen X'ers have seen enough gold rushes to know the real thing. This one's got all the usual crap—bad actors, inflated claims, VCs throwing money at anything with "AI" in the pitch deck. Gross behavior all around. Normal for a paradigm shift, but still gross.
The people who helped wire up the internet recognize what's happening. When the folks who've been through every tech cycle since gopher start acting like excited newbies again, that tells you something.
Reverse engineering some updates to Claude
Anthropic released two major new features for their consumer-facing Claude apps in the past couple of days. Sadly, they don’t do a very good job of updating the release notes for those apps—neither of these releases came with any documentation at all beyond short announcements on Twitter. I had to reverse engineer them to figure out what they could do and how they worked!
[... 1,685 words]