Viewing profile — usagisushi
usagisushi
HN member- Joined
- Mon, Nov 11, 2024, 1:47 PM UTC
- HN karma
- 112
- Public activity
- 65 items
- HN profile
- View on Hacker News ↗
About usagisushi
No profile information was provided.
Recent public activity
-
comment
Comment #49267925
If you haven't yet, you might want to try gemma-4-E4B-it-qat or gemma-4-12B-it-qat with Structured Outputs. My main use case is tagging photos and generating headlines.
-
comment
Comment #49195121
[dead]
-
comment
Comment #49153730
[dead]
-
comment
Comment #49143620
[dead]
-
comment
Comment #49109480
While the ESP32 does have a high inrush current, its ULP coprocessor is quite capable, drawing only 12µA@3.3V during Deep Sleep. I have a fleet of AA-powered ESP32 devices at home …
-
comment
Comment #48992698
A recursive way to burn the tokens.
-
comment
Comment #48990877
Agencies are helpful for the tech and business side, sure, but as the article mentions, the indie scene has exploded. Plenty of creators are putting out high-quality stuff entirely…
-
comment
Comment #48965325
Neat! I recently wrote a weather app for System 3.x using autc04/Retro68[1]. I've been planning to create an original set of weather icons, so this is exactly the kind of reference…
-
comment
Comment #48965263
The API endpoints on this page accept an OAuth token from ~/.codex/auth.json. You can simply ask Codex to create a report skill with some curl examples.
-
comment
Comment #48906524
I’ve previously used luakit browser [1] with cage WM [2] on a Pi Zero 2 W for my clock build, and it worked quite well. [1]: https://github.com/NixOS/nixpkgs/blob/nixos-24.11/pkgs/…
-
comment
Comment #48870453
[dead]
-
comment
Comment #48856653
Tip: You can see the token usage of MCPs/plugins/skills by using `/context`. For example, the M$ 365 MCP occupies several thousands of tokens, and there's currently no way to disab…
-
comment
Comment #48832270
For Japanese TTS, AivisSpeech-Engine[1] works really well with mixed Japanese/English text in my experience. They also provide container images on ghcr.io for both CPU and GPU infe…
-
comment
Comment #48783738
[dead]
-
comment
Comment #48700091
Not the OP, but their setup must be faster than my 4060 16GB + 3060 12GB setup. Here are my numbers (typical values, N=1): Model pp (t/s) tg (t/s) Qwen 3.6 27B 900 29 Qwen 3.6 35B-…
-
comment
Comment #48675506
Back in 2014, Son also gave me a good laugh with a slide comparing: > Von Neumann computer: powered by programming vs. Personal robot: powered by family happiness. https://i.gzn.jp…
-
comment
Comment #48585489
My grandma had a Paraguayan snuffler (specifically Emunctator sorbens ), these parasitoids were his absolute favorite snack.
-
comment
Comment #48319452
Lime-Limiting Machine
-
comment
Comment #48239000
I pretty much agree. While any semblance of a "horizontal" dynamic in Japanese software development was perhaps realized in embedded systems around 40 years ago (e.g., rice cookers…
-
comment
Comment #48191339
Practically, it's not limited to GitHub Pages, though. By the way, even while a custom domain is still pending verification, the GitHub Pages LB will route the request based on the…
- story
- comment
-
comment
Comment #48020488
Yeah, I’ve used a similar technique to build a "pizza clock" before (where the number of slices corresponds to the hours).
-
comment
Comment #47924531
If the "loop" you mean is the infinite reasoning cycle ("Wait, actually... On second thought..."), you might want to try setting a reasoning budget. For llama.cpp, use `--reasoning…
-
comment
Comment #47900633
Yeah, now it's USB4 Version 2.0 / USB 80Gbps / USB4 Gen4.