It's the typestate pattern. The compiler enforces valid state transitions and so you can't just pass to the same function. It's useful to ensure that only some transitions are allowed. To be honest, the connection state presented by GP is a bad example. But you shouldn't say "it defeats the point".
A better example is an HTTP writer. One state is `Headers` with the methods `add_header()` and `body()` which returns the response in state `Body`. This enforces that one can't add headers after `body()` has been called. But you can finish the response in the `Body` state. If you do something not in this order, you get a compile error.
I noticed that when opus 5.5 was on parts on my codebase that had lots of 5.0-generated comments, it picked up its style. Unfortunately I think 5.5 has been trained to mimic what it sees so that you can ease up on the instructions, but this does mean parts of your codebase that 5 touched will be somewhat viral.
I gave it some vibecoded patch someone created with Opus 5 with the task of together figuring out the real root cause and what to do about it.
Big mistake. The rest of the session was all claude-speak up until I've rage-quit and restarted with Qwen and no context other than "here's what I think we've missed in the current implementation. How could we approach that?"
GLM felt like it got at least 20 IQ points dumber just from being exposed to claude's writing.
I almost wonder if Claude reads that it “keeps responses focused, brief, and concise” and interprets that as built-in behavior and concludes that it doesn't need to spend additional effort enforcing it, just as it doesn't need to expend effort being “accessible via this web-based, mobile, or desktop chat interface”.
Claude doesn't "interpret" anything. That's not how LLMs work. They are still sentence completing machines. You give input in, the model network fires the chain that produces the most likely related output. That's it.
I think you might be right, though that this would have influence on other output tokens since it is phrased as a substantive property, rather than an instruction.
1. We don't need to connect every nook and corner with public transit. Each city having its own would be sufficient. 2. The US is sparse _because_ of cars: the space allocated for parking pushes things apart.
The models themselves have far from plateaued. Maybe someone finds a way to get a really capable model down to, say, 12GB of ram. Then we'd be in business.
Agreed. We've just seen DeepSeek post-train their ~300 billion parameter flash model to outperform their 1.6 trillion parameter pro model, in the space of a few months. There would seem to still be quite a few opportunities on the table to bring big model smarts down to the smaller models
reply