w2c2 has only 2 mentions. wasm2c is not a clear winner, it's specifically losing several of their benchmarks.

In general, using a preexisting compiler as a JIT backend is an old hack, there's nothing new there. It's just another JIT/AoT backend. For example, databases have done query compilation for probably decades by now.

Browsers are sandboxed by the kernel, and we're talking about bugs in the kernel here...

Even if modern browsers lean more on kernel features, initially the sandboxing in browsers is implemented through a managed runtime.

> It’s also worth noting that Rust doesn’t prevent integer overflow

Add a single line to a single file and you get that enforced.

https://rust-lang.github.io/rust-clippy/stable/index.html#ar...

WASM, and asm.js before it, roughly exist because Javascript is such a bad compile target.

> You also have to have the right high level language to do this kind of DOM interaction and application logic.

That just means you personally like JS. In my opinion many languages are better than it.

Part of that is likely that Claude Code tools keep changing a little. Imitating them is chasing a moving target.

> Any idea on why the other end of the spectrum is this way -- thinking that it always has something to do?

Who said anything about "thinking"? Smaller models were notorious for getting stuck repeating a single word over and over, or just "eeeeeee" forever. Larger models only change probabilities, not the fundamental nature of the machine.

Claude Code is more than the TUI, it's the prompts, the agentic loop, and tools, all made to cooperate well with the LLM powering it. If you use Claude Code over a longer period of time you'll notice Anthropic changing the tooling and prompts underneath it to make it work better. By now, the model is tuned to their prompts, tools etc.

> They need a guarantee

s/need/want/ but yes.

I really wish more people would appreciate this distinction.

In this case, you verify whether the knowledge was made up by comparing the virtual waiter behaviour to the actual waiter. Having a strong test suite like that is actually the ideal scenario for agentic development.

(It still incredibly hard to pull off for real, because of complex stateful protocols and edge cases around timing and transfer sizes. Samba did take 12 years to develop, so even with LLM help you'd probably still be looking at several years.)