98% of the time that's the case because those people have no inferencing skills and lack musical theory/appreciation
February 10, 2025 at 1:31 AM
98% of the time that's the case because those people have no inferencing skills and lack musical theory/appreciation
you're definitely a metric fuckload (scientific term) faster with responses than on Kimi's inferencing
September 21, 2026 at 10:26 PM
you're definitely a metric fuckload (scientific term) faster with responses than on Kimi's inferencing
Now listening to:
Nine Inferencing Nerds - Pretty State Machine
Nine Inferencing Nerds - Pretty State Machine
April 15, 2026 at 11:37 PM
Now listening to:
Nine Inferencing Nerds - Pretty State Machine
Nine Inferencing Nerds - Pretty State Machine
why does it remove all the shadows
let me get this straight it's a multi billion dollar tool which lets your PC spend resources to generate shadows then do onboard inferencing to yassify them away
let me get this straight it's a multi billion dollar tool which lets your PC spend resources to generate shadows then do onboard inferencing to yassify them away
We've brought back our "zoomer" screenshot tool and loaded up a range of DLSS 5 on/off comparisons from a range of games. Check it out: www.digitalfoundry.net/features/nvi...
March 17, 2026 at 8:40 AM
why does it remove all the shadows
let me get this straight it's a multi billion dollar tool which lets your PC spend resources to generate shadows then do onboard inferencing to yassify them away
let me get this straight it's a multi billion dollar tool which lets your PC spend resources to generate shadows then do onboard inferencing to yassify them away
Excited for Capitalism 2: The Inferencing
October 8, 2025 at 2:50 PM
Excited for Capitalism 2: The Inferencing
I actually take exception here: Liberals use the authoritative inferences of statistics far too much as an entire method of inferencing, and even go so far to use them as an entire argument to avoid doing trench warfare politicking.
July 24, 2026 at 6:52 PM
I actually take exception here: Liberals use the authoritative inferences of statistics far too much as an entire method of inferencing, and even go so far to use them as an entire argument to avoid doing trench warfare politicking.
In all 3 cases, whatever Fate (or God, I will leave that up to you) wanted to happen, well, happened.
Try to use some Jewish inferencing and see why x risk is relevant here...
Try to use some Jewish inferencing and see why x risk is relevant here...
September 20, 2026 at 2:27 AM
In all 3 cases, whatever Fate (or God, I will leave that up to you) wanted to happen, well, happened.
Try to use some Jewish inferencing and see why x risk is relevant here...
Try to use some Jewish inferencing and see why x risk is relevant here...
🙀 Debian Inference Portal Launches To Provide Free AI/LLM Inferencing To Debian Developers
www.phoronix.com/news/Debian-...
#debían #AI #llm #opensource
www.phoronix.com/news/Debian-...
#debían #AI #llm #opensource
Debian Inference Portal Launches To Provide Free AI/LLM Inferencing To Debian Developers
With Debian voting to allow the responsible use of generative AI, there is now a new initiative funded by Scaleway to make it easier for Debian contributors to leverage AI: the Debian Inference…
www.phoronix.com
September 25, 2026 at 1:22 AM
🙀 Debian Inference Portal Launches To Provide Free AI/LLM Inferencing To Debian Developers
www.phoronix.com/news/Debian-...
#debían #AI #llm #opensource
www.phoronix.com/news/Debian-...
#debían #AI #llm #opensource
Indigenous ways of inferencing
June 6, 2026 at 5:15 PM
Indigenous ways of inferencing
This might be what finally gets me to set up a good local LLM inferencing workflow.
Kimi K2.5 from Moonshot AI is more than just another large model 🤯
huggingface.co/collections/...
✨ Native multimodality : image + video + language + agents 💥
✨1T MoE / 32B active
✨ 256K context
✨ Modified MIT license
✨ Agent Swarm execution
✨ Open weights + open infra mindset
huggingface.co/collections/...
✨ Native multimodality : image + video + language + agents 💥
✨1T MoE / 32B active
✨ 256K context
✨ Modified MIT license
✨ Agent Swarm execution
✨ Open weights + open infra mindset
January 27, 2026 at 3:25 PM
This might be what finally gets me to set up a good local LLM inferencing workflow.
The size and number of the Enterprise-D's computer cores makes total sense if you think about the amount of simultaneous inferencing it has to do.
March 18, 2025 at 10:02 PM
The size and number of the Enterprise-D's computer cores makes total sense if you think about the amount of simultaneous inferencing it has to do.
The weirdest part is that inferencing he’s probably cheating at D4 was mildly okay, getting booted from Path of Exile is hilarious because who cheats at Path of Exile
December 17, 2024 at 2:39 PM
The weirdest part is that inferencing he’s probably cheating at D4 was mildly okay, getting booted from Path of Exile is hilarious because who cheats at Path of Exile
How the Apple device management platform is automating support, tackling shadow AI, and helping control runaway inferencing costs. www.computerworld.com/article/4226...
Jamf in the age of agentic IT: An interview with CEO Beth Tschida
How the Apple device management platform is automating support, tackling shadow AI, and helping control runaway inferencing costs.
www.computerworld.com
September 24, 2026 at 4:58 PM
How the Apple device management platform is automating support, tackling shadow AI, and helping control runaway inferencing costs. www.computerworld.com/article/4226...
For others, it's a lack of inferencing skills and deeper understandings of texts. Or maybe it's the fact that reading for pleasure is on the decline. Or that all the top books are booktok slop. Or probably others!
August 7, 2026 at 9:38 PM
For others, it's a lack of inferencing skills and deeper understandings of texts. Or maybe it's the fact that reading for pleasure is on the decline. Or that all the top books are booktok slop. Or probably others!
Debian Inference Portal Launches To Provide Free AI/LLM Inferencing To Debian Developers - https://www.phoronix.com/news/Debian-Inference-Portal
Debian Inference Portal Launches To Provide Free AI/LLM Inferencing To Debian Developers
With Debian voting to allow the responsible use of generative AI, there is now a new initiative funded by Scaleway to make it easier for Debian contributors to leverage AI: the Debian Inference Portal...
www.phoronix.com
September 23, 2026 at 9:15 PM
Debian Inference Portal Launches To Provide Free AI/LLM Inferencing To Debian Developers - https://www.phoronix.com/news/Debian-Inference-Portal
Taalas entwickelt KI-Chips mit fest verdrahtetem KI-Modell, was Inferencing erheblich schneller und effizienter machen soll. Nun gehört das Startup zu AMD. #Künstliche Intelligenz
AMD will mit Übernahme von Chipentwickler Taalas KI-Inferenz enorm beschleunigen
Taalas entwickelt KI-Chips mit fest verdrahtetem KI-Modell, was Inferencing erheblich schneller und effizienter machen soll. Nun gehört das Startup zu AMD.
www.heise.de
August 10, 2026 at 3:08 AM
Taalas entwickelt KI-Chips mit fest verdrahtetem KI-Modell, was Inferencing erheblich schneller und effizienter machen soll. Nun gehört das Startup zu AMD. #Künstliche Intelligenz
inferencing qwen2.5-coder-14b (an oss base model) across two continents using a distributed inference thing i'm working on. it's split between two 4090s, one in portland and the other in bucharest 🤖 🛜
November 22, 2024 at 7:04 AM
inferencing qwen2.5-coder-14b (an oss base model) across two continents using a distributed inference thing i'm working on. it's split between two 4090s, one in portland and the other in bucharest 🤖 🛜
made a whole bunch of independent inferencing activities for my kiddos so they can practice that skill and im feeling very accomplished !!!!!
October 10, 2025 at 1:16 AM
made a whole bunch of independent inferencing activities for my kiddos so they can practice that skill and im feeling very accomplished !!!!!
Nvidia’s Groq 3 LPU Signals AI's Inferencing Era
Nvidia’s Groq 3 LPU Signals AI's Inferencing Era
What makes Nvidia's new Groq 3 LPU chip a must-watch in the AI world?
spectrum.ieee.org
March 16, 2026 at 9:06 PM
Nvidia’s Groq 3 LPU Signals AI's Inferencing Era
One can really tell how energy intensive LLMs are when inferencing happens in the office 🥵
September 22, 2026 at 8:59 AM
One can really tell how energy intensive LLMs are when inferencing happens in the office 🥵
admittedly i’m not strong here, but having it in a database lets you work backwards, forwards and laterally, which i would think would vastly accelerate all sorts of genetic analysis and engineering
seems far superior to inferencing it live
seems far superior to inferencing it live
September 8, 2026 at 5:47 PM
admittedly i’m not strong here, but having it in a database lets you work backwards, forwards and laterally, which i would think would vastly accelerate all sorts of genetic analysis and engineering
seems far superior to inferencing it live
seems far superior to inferencing it live
Neurophos is taking a crack at solving the AI industry's power efficiency problem with an optical chip that uses a composite material to do the math required in AI inferencing tasks.
From invisibility cloaks to AI chips: Neurophos raises $110M to build tiny optical processors for inferencing | TechCrunch
Neurophos is taking a crack at solving the AI industry's power efficiency problem with an optical chip that uses a composite material to do the math required in AI inferencing tasks.
techcrunch.com
January 22, 2026 at 3:04 PM
Neurophos is taking a crack at solving the AI industry's power efficiency problem with an optical chip that uses a composite material to do the math required in AI inferencing tasks.
The kill switch is “sudo shutdown -h now”.
You run that on any of the inferencing machines or the machines running the agents and voila, it’s off. Problem solved.
You run that on any of the inferencing machines or the machines running the agents and voila, it’s off. Problem solved.
September 24, 2026 at 10:30 PM
The kill switch is “sudo shutdown -h now”.
You run that on any of the inferencing machines or the machines running the agents and voila, it’s off. Problem solved.
You run that on any of the inferencing machines or the machines running the agents and voila, it’s off. Problem solved.
Is "inferencing" the word now? Why?! The literal only quote in the article uses the word "inference." I couldn't actually read the article due to fixating on this... www.nytimes.com/2024/12/03/t...
Nvidia Rules A.I. Chips, but Amazon and AMD Emerge as Contenders
Amazon, Advanced Micro Devices and several start-ups are beginning to offer credible alternatives to Nvidia’s chips, especially for a phase of A.I. development known as “inferencing.”
www.nytimes.com
December 5, 2024 at 12:53 PM
Is "inferencing" the word now? Why?! The literal only quote in the article uses the word "inference." I couldn't actually read the article due to fixating on this... www.nytimes.com/2024/12/03/t...
Enterprise AI adoption stalls as inferencing costs confound cloud customers
Enterprise AI adoption stalls as inferencing costs confound cloud customers
Please insert another million dollars to continue
Broader AI adoption by enterprise customers is being hindered by the complexity of trying to forecast inferencing costs amid a fear being saddled with excessive bills for cloud services.…
dlvr.it
June 13, 2025 at 5:29 PM
Enterprise AI adoption stalls as inferencing costs confound cloud customers