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