codemk8
Re:Qwen3.8-Max: A New Bar for Coding and Cowork
on Monday August 03, 2026 @12:49PM (#49158250)
This post exactly ;-)
Re:DeepSeek-V4-Flash Update
on Friday July 31, 2026 @01:58PM (#49126514)
Me.
Re:Kimi K3 Is Competitive with Fable; Kimi K3 and Fable Is SoTA
on Wednesday July 22, 2026 @09:26AM (#49006439)
If I had an oracle, why would I need an LLM?
Re:Ask HN: Has anyone replaced Claude/GPT with a local model for daily...
on Monday June 15, 2026 @06:42PM (#48548043)
You mean deepseek-v4-flash, right? Same here. I use it for my Hermes agent. It's so cheap that I sometimes feel "guilty". I even put more money than I needed just make sure they do not go out of business.
Re:Ask HN: What is the cheapest ($/hour) H100 renting service with qui...
on Sunday October 27, 2024 @09:24AM (#41962467)
Runpod with its python APIs.
Re:AMD May Get Across the CUDA Moat
on Sunday October 08, 2023 @11:03AM (#37811104)
From my recent experience, ROCm and hipcc allow you to port cuda programs fairly easily to AMD arch. The compiling is so much faster than nvcc too.
Re:The next Google
on Tuesday April 05, 2022 @01:35PM (#30922146)
This reminds me of the user interface for pied piper’s compression algorithm
Re:Animal Populations Fell by 68% in 50 Years and It’s Getting Worse
on Thursday September 10, 2020 @10:17AM (#24432585)
Expecting the Netflix show of this book though.
Re:Wuhan coronavirus: From silent streets to packed pools
on Tuesday August 18, 2020 @01:22PM (#24201441)
Lol I posted the same link 2 mins after u
Re:Wuhan coronavirus: From silent streets to packed pools
on Tuesday August 18, 2020 @01:19PM (#24201401)
A recent report from New Yorker
https://www.newyorker.com/magazine/2020/08/17/how-china-cont...
Re:New Compute Engine A2 VMs–First Nvidia Ampere A100 GPUs in the Cloud
on Tuesday July 07, 2020 @03:08PM (#23762869)
Agree. That is theoretical speed up. Most applications are bandwidth bounded thus cannot get that ratio.
Re:New Compute Engine A2 VMs–First Nvidia Ampere A100 GPUs in the Cloud
on Tuesday July 07, 2020 @03:04PM (#23762832)
The GeForce makes huge difference here.
Re:New Compute Engine A2 VMs–First Nvidia Ampere A100 GPUs in the Cloud
on Tuesday July 07, 2020 @01:01PM (#23761258)
For azure, NC is for vms with NVidia card. Seems that they deliberately choose different terms.
Re:Nvidia CEO Introduces Nvidia Ampere Architecture, Nvidia A100 GPU
on Thursday May 14, 2020 @12:11PM (#23181259)
Agree. The reason GPUs are not widely adopted in certain areas is not because of open sourced or not, but because it is not cost effective. GPUs are optimized for throughput, not latency.