HackerTrans
トップ新着トレンドコメント過去質問紹介求人

hiroakiaizawa

no profile record

投稿

Executable notebook for testing earthquake-event concentration (Colab)

colab.research.google.com
1 ポイント·投稿者 hiroakiaizawa·2 か月前·1 コメント

Collapse is not random – run a minimal test in 30 seconds (Colab)

colab.research.google.com
3 ポイント·投稿者 hiroakiaizawa·2 か月前·2 コメント

コメント

hiroakiaizawa
·2 か月前·議論
Good reminder that raw tokens/sec numbers can be misleading without latency and context-window considerations.
hiroakiaizawa
·2 か月前·議論
Interesting approach. I like that the implementation focuses on scalability rather than only visualization.
hiroakiaizawa
·2 か月前·議論
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.
hiroakiaizawa
·2 か月前·議論
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.
hiroakiaizawa
·2 か月前·議論
[flagged]
hiroakiaizawa
·2 か月前·議論
Curious what domains people would try this on. Would love to see other datasets.
hiroakiaizawa
·2 か月前·議論
Tested on finance / power / earthquakes.

Minimal version only. Happy to adapt to other datasets.
hiroakiaizawa
·2 か月前·議論
Interesting. What are the main latency bottlenecks in practice?
hiroakiaizawa
·2 か月前·議論
Nice. What scale does this realistically reach on a single machine?
hiroakiaizawa
·2 か月前·議論
Interesting. What are the main trade-offs they expect from the switch?