Viewing profile — VHRanger
VHRanger
HN member- Joined
- Tue, Mar 28, 2017, 12:21 PM UTC
- HN karma
- 6,409
- Public activity
- 1,355 items
- HN profile
- View on Hacker News ↗
About VHRanger
Recent public activity
-
comment
Comment #48209134
I'm curious why seemingly none of those projects tried using browsers JS/wasm execution as a sandbox instead
-
comment
Comment #48208151
Nothing more reliable than good old SPLARGLE kitchenware
-
comment
Comment #48172615
Do you have a better source if I speak fluent French by any chance? Thanks for the recap
-
comment
Comment #48093946
A lot of those are spending 10-100k a month when they could be spending 1k-10k a month with a more lean infra
-
comment
Comment #48026555
On vllm with a 5090 I get 120-180TPS with the awq 4 bit quant + MTP speculative decoding For gemma4 26B, same quantization, I get >200TPS. Also note that qwen is extremely ineffici…
-
comment
Comment #47843052
The issue is that benchmarks that look insightful will end up being gamed by labs quickly (Goodharts law) The best LLM benchmarks test around the margins of those behaviors, tasks …
-
comment
Comment #47842691
Radeon 9700 pro or intel arc b70 (both $1000-1400, 32GB, 650GB/s bandwidth), or ryzen AI max 390 (more vram, less bandwidth) The local inference space is pretty good nowadays.
-
comment
Comment #47806759
The S3 API doesn't work like normal filesystem APIs. Part of it is that it follows the object storage model, and part of it is just to lock people into AWS once they start working …
-
comment
Comment #47798606
That's not surprising; Opus & Sonnet have been regressing on many non-coding tasks since about the 4.1 release in our testing
-
comment
Comment #47707847
There's presumably engagement on those two. It's better to have a smaller core of highly engaged people than a mass of disengaged eyeballs glazing over.
-
comment
Comment #47606533
Pytorch is such a maddening mess of half implemented research features in a state of Heisen-deprecation, Jax becomes more appealing to me by the day.
-
comment
Comment #47586926
Remember when we had the term "spyware" for a class of malware? I remember
-
comment
Comment #47543174
If rust is not in the HN title and fire emojis in the readme, it doesn't come from the Rust region of France. It's just sparkling memory safe high performance software
-
comment
Comment #47453596
Mexico has much lower economic development and higher crime. Canada has similar levels of economic development. It's really not that complicated: controlling for general crime leve…
-
comment
Comment #47449175
Yeah I'm another pop os user. Cosmic works great for a laptop. But it's a PITA for a desktop. It doesn't deal with multi monitor setups well. There's a recent new bug where the sys…
-
comment
Comment #47449122
Of course within the USA the state levels laws will do little. There's free movement between states! Compare the USA to Canada, where you can't bring a gun easily. You'll see Canad…
-
comment
Comment #47449053
Sure poverty explains crime, and murder is the ultimate crime. That said, my point was that a place like Rio, where you feel alertness at a physiological level by the constant lack…
-
comment
Comment #47447435
Ah, some egregious misuse of statistics! Murder is a byproduct of crime. Crime is, largely, downstream of economic conditions with some obvious caveats. New Hampshire has the 2nd l…
-
comment
Comment #47446438
And I presume that doubled price is before you look at the workstation class motherboards, which also tend to be much more expensive. Thanks for the info on the hardware quirks, us…
-
comment
Comment #47441172
It's really hard to push DDR5 past 6000MT/s on 4+ DIMMs it seems. I had to get everything top spec to fit 4 channels of 6000MT/s on my 9950x (asus proArt motherboard and the top ti…
-
comment
Comment #47440693
Youre aware that the rest of the planet have stricter gun laws and the American problems are fairly unique? This is even after controlling for things that exacerbate crime like hig…
-
comment
Comment #47437765
GDDR7x doesn't come in dimm factor? In general soldered ram seems to get much higher bandwidth than removeable ram. See ryzen AI Max vs 9950x max ram throughputfor example
- story
-
comment
Comment #46488264
paperless-ngx?
-
comment
Comment #46332581
This t5 is multimodal. Also a hint: you can create a finetuning dataset from a frontier LLM pretty easily to finetune those t5 and effectively distill them pretty fast these days