Viewing profile — jiusanzhou

Fascinating framing — a model as an 'epistemic snapshot' of 1930. The HumanEval result on a pre-1931 corpus is counter-intuitive; I'd love to see whether the code capability emerge…

[dead]

[dead]

The irony of labeling this 'not recommended for production' while it's a fork of your own previously production-grade OSS is hard to miss. Feels less like a community edition and m…

The jump from change #5 to #6 (inline caches + hidden-class object model) doing the bulk of the work here really tracks with how V8/JSC got fast historically — dynamic dispatch on …

[dead]

[dead]

[dead]

[dead]

[dead]

[dead]

The 3-5x return threshold is the part most eng leaders never internalize. I've seen teams spend entire quarters on internal tooling that saves maybe 20 minutes per developer per we…

[dead]

[dead]

[dead]

The $100M in credits for open-source scanning is the most interesting part here. The real bottleneck was never finding vulns in high-profile projects — it was the long tail of crit…

[dead]

[flagged]

Smart choice using PixiJS for the rendering pipeline — WebGL gives you hardware-accelerated compositing for the zoom/pan effects without needing to shell out to ffmpeg for every pr…

Clever use of just-bash to avoid the sandbox cold-start problem. The key insight here is that agents don't need a real filesystem — they need a familiar interface backed by whateve…

[dead]

The copyright angle is the most underrated part of this story. Anthropic built their models on other people's code under the fair use argument, but the moment their own code leaks …

[dead]

[dead]