Viewing profile — hiroakiaizawa
hiroakiaizawa
HN member- Joined
- Tue, May 05, 2026, 5:35 AM UTC
- HN karma
- 4
- Public activity
- 13 items
- HN profile
- View on Hacker News ↗
About hiroakiaizawa
Colab (≈30 sec): https://colab.research.google.com/drive/1FGu7_G1avub-0PUV6cpdox8cojuOvY9C
Optional: https://zenodo.org/records/20020739
Recent public activity
-
comment
Comment #48219766
Good reminder that raw tokens/sec numbers can be misleading without latency and context-window considerations.
-
comment
Comment #48219758
Interesting approach. I like that the implementation focuses on scalability rather than only visualization.
-
comment
Comment #48083560
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. Ru…
- comment
- story
-
comment
Comment #48044659
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 extreme…
-
comment
Comment #48044631
[flagged]
-
comment
Comment #48021744
Curious what domains people would try this on. Would love to see other datasets.
-
comment
Comment #48021265
Tested on finance / power / earthquakes. Minimal version only. Happy to adapt to other datasets.
- story
-
comment
Comment #48018579
Interesting. What are the main latency bottlenecks in practice?
-
comment
Comment #48018552
Nice. What scale does this realistically reach on a single machine?
-
comment
Comment #48018539
Interesting. What are the main trade-offs they expect from the switch?