News for hackers. Stuff that matters.

hiroakiaizawa

Re:How fast is N tokens per second really? on Thursday May 21, 2026 @05:03AM (#48219766)
Good reminder that raw tokens/sec numbers can be misleading without latency and context-window considerations.
Interesting approach. I like that the implementation focuses on scalability rather than only visualization.
The notebook is intentionally minimal.

Not a prediction model or causal explanation — just a reproducible concentration check with fixed ex-ante definitions and minimal outputs.

Runs in ~30 sec on Colab.

One thing I've started appreciating with LLM-assisted workflows is how important fixed evaluation protocols are.

Without pre-defined definitions and locked procedures, it's extremely easy to mistake iterative adaptation for genuine signal.

Curious what domains people would try this on. Would love to see other datasets.
Tested on finance / power / earthquakes.

Minimal version only. Happy to adapt to other datasets.

Re:How OpenAI delivers low-latency voice AI at scale on Tuesday May 05, 2026 @01:52AM (#48018579)
Interesting. What are the main latency bottlenecks in practice?
Re:Train Your Own LLM from Scratch on Tuesday May 05, 2026 @01:48AM (#48018552)
Nice. What scale does this realistically reach on a single machine?
Re:Bun is being ported from Zig to Rust on Tuesday May 05, 2026 @01:46AM (#48018539)
Interesting. What are the main trade-offs they expect from the switch?