sillyboi

Right, the article is about the website. I was responding to the comments up there about the iOS app doing the same thing in the background, but I didn't catch the little bit with the reply.

I thought the App Store review guidelines explicitly prohibit hidden features and using public APIs outside their intended purpose. Is audio-based fingerprinting just not something review can realistically catch?

It would be awesome to put an interactive example right in the article.

Why don't SSDs trust websites anymore?

Because every time they open up, the site gives them the F̶R̶O̶S̶T̶ cold shoulder.

I just tried Opus 4.8 (Ultracode xhigh + workflows), and it started throwing an error no matter what I sent to the chat: "API Error: 400 message.1.content.4: thinking or redacted_thinking blocks in the latest assistant message cannot be modified. These blocks must remain as they were in the original response."

Nice work. It's refreshing to see a simple and local-first Tauri app instead of another one CLI/TUI tool.

It feels like a change in department leadership and management, or an internal power struggle over a lucrative piece of the project (with all the consequences that typically come with it). In the end, it seems more about satisfying personal egos than serving the product, and the end users will be the ones left to “appreciate” the results.

Oh, another new trend! I love these home-brewed LLM optimizers. They start with XML, then JSON, then something totally different. The author conveniently ignores the system prompt that works for everything, and the extra inference work. So, it's only worth using if you just like this response style, just my two cents. All the real optimizations happen during model training and in the infrastructure itself.

There's a Doom Box plan but no Boom Box

The real win here isn’t just performance,it’s convergence.

When ReadableStream behaves the same in the browser, Workers, and other runtimes, stream-based code becomes portable and predictable. That reduces subtle backpressure bugs and eliminates “works here but not there” edge cases.

Standardization at the streams layer is a big deal for building reliable streaming systems across environments.

Sgai pronounced “Sky.” The letters “S” and “G” just showed up to watch.

I’d like to add an obvious point that is often overlooked.

LLMs take on a huge portion of the work related to handling context, navigating documentation, and structuring thoughts. Today, it’s incredibly easy to start and develop almost any project. In the past, it was just as easy to get overwhelmed by the idea of needing a two-year course in Python (or any other field) and end up doing nothing.

In that sense, LLMs help people overcome the initial barrier, a strong emotional hurdle, and make it much easier to engage in the process from the very beginning.