Viewing profile — GrayShade
GrayShade
HN member- Joined
- Sat, Jul 30, 2016, 1:30 PM UTC
- HN karma
- 1,382
- Public activity
- 445 items
- HN profile
- View on Hacker News ↗
About GrayShade
No profile information was provided.
Recent public activity
-
comment
Comment #49184813
https://qwen.ai/blog?id=qwen-image-3.0 https://news.ycombinator.com/item?id=48989701
-
comment
Comment #48437132
On systemd, you can use ~/.config/environment.d to set it. Don't rely on your shell.
-
comment
Comment #47966703
Fedora is patched.
-
comment
Comment #47802722
I get 20 t/s on the UD-Q6_K_XL quant, Radeon 6800 XT.
-
comment
Comment #47761182
It only supports CUDA on Linux.
-
comment
Comment #47737749
You can, after you unlock it.
-
comment
Comment #47687551
We've had shitty bloated websites before LLMs were a thing.
-
comment
Comment #47649420
It's plain FUD. systemd always had fields for the full name, email address and location. They were optional, just like the date of birth. Bad systemd!
-
comment
Comment #47591476
The operating system does not need to know your full name, email and location in order to manage your hardware and software, yet systemd has had optional fields for those for years…
-
comment
Comment #47545402
It's easier to torrent stuff than to get 4K in Netflix on Linux.
-
comment
Comment #47503957
1.82.7 doesn't have litellm_init.pth in the archive. You can download them from pypi to check. EDIT: no, it's compromised, see proxy/proxy_server.py.
-
comment
Comment #47499555
It's gone: https://github.com/bjarneo/cliamp/commit/085734a86343a80176d...
-
comment
Comment #47465830
Don't forget location.
-
comment
Comment #47465805
It doesn't, and it's optional.
-
comment
Comment #47368052
Looks like it's a bit slower today. Running llama.cpp b8192 Vulkan. $ ./llama-cli unsloth_Qwen3.5-35B-A3B-GGUF_Qwen3.5-35B-A3B-UD-Q4_K_XL.gguf -c 65536 -p "Hello" [snip 73 lines] […
-
comment
Comment #47367047
That's not a shell, it's a Python interpreter compiled to WASM and running in the browser.
-
comment
Comment #47366318
This feels a bit pessimistic. Qwen 3.5 35B-A3B runs at 38 t/s tg with llama.cpp (mmap enabled) on my Radeon 6800 XT.
-
comment
Comment #47319946
And footnote 3 is unreferenced.
-
comment
Comment #47286941
It did, there's two incompatible approaches, zram and zswap.
- story
-
comment
Comment #47231313
The Signal device linking feature is just as fast. It's partly a trick -- it will look for QR codes even outside the central area, so under good conditions it can get a read before…
-
comment
Comment #47075315
Maybe that's the only API-visible change, saying nothing about the actual capabilities of the model?
-
comment
Comment #47027723
This patch uses a DNS extension to report the running version and check for updates. The messages are encrypted in flight. The feature is gated at build-time, and enabled in the pa…
- story
-
comment
Comment #46715602
The indexer was probably clangd, not Code itself.