HackerTrans
TopNewTrendsCommentsPastAskShowJobs

hiroakiaizawa

no profile record

Submissions

Executable notebook for testing earthquake-event concentration (Colab)

colab.research.google.com
1 points·by hiroakiaizawa·2 ay önce·1 comments

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

colab.research.google.com
3 points·by hiroakiaizawa·2 ay önce·2 comments

comments

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

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