Executable notebook for testing earthquake-event concentration (Colab)colab.research.google.com1 points·by hiroakiaizawa·2 mesi fa·1 comments
Collapse is not random – run a minimal test in 30 seconds (Colab)colab.research.google.com3 points·by hiroakiaizawa·2 mesi fa·2 comments
hiroakiaizawa·2 mesi fa·discussGood reminder that raw tokens/sec numbers can be misleading without latency and context-window considerations.
hiroakiaizawa·2 mesi fa·discussInteresting approach. I like that the implementation focuses on scalability rather than only visualization.
hiroakiaizawa·2 mesi fa·discussThe 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 mesi fa·discussOne 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 mesi fa·discussCurious what domains people would try this on. Would love to see other datasets.
hiroakiaizawa·2 mesi fa·discussTested on finance / power / earthquakes.Minimal version only. Happy to adapt to other datasets.
hiroakiaizawa·2 mesi fa·discussInteresting. What are the main trade-offs they expect from the switch?