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