iOS 26 Beta 5 comes with a new design: liquid rubber.

vLLM has put up a recipe for gpt-oss. It details all the limitations. My investigation from yesterday was correct. `chat/completions`doesn't support tool calls at all. That means tools like opencode, qwen-cli, crush, etc. won't work. Armin Ronacher ⇌ docs.vllm.ai/projects/recip…

optimism wins

If the gpt-oss release was any indication, brace yourself for a timeline of fast and uninformed takes today.

This project has no uv reference, but cursor with gpt-5 decided to try to use uv first. That's a first and I welcome this.

I understand why they do it, but I'm not a fan of taking away the old models immediately. Particularly because the system prompts are also largely kept a secret, so it's very hard to replicate what o3/o4-mini did in the API.

Does anyone know if there is a price comparison of the different models for some standard agentic tasks (eg: in opencode)? Token cost is not alone particularly useful because depending on the model, it's going to pull in more or less into the context etc.

I'm very happy to see that cursor-agent implements my favorite claude-code feature

ChatGPT on Plus old: ~100 o3/week, ~100 o4-mini-high/day. Today: ~200 thinking/week. Not sure how this will play out, but has a o4-mini-high hardcore user on plus I'm guessing this will mean I will lose out compared to what I had :(

Recorded some updated thoughts on agentic coding tools if someone is curious.