Ladioss
Re:Semgrep: GLM 5.2 beats Claude in our Cyber Benchmarks
on Monday June 29, 2026 @04:11AM (#48716258)
"Best model" discourse always remember me of my days in Monster Hunter with people who refused to consider playing with anything other than the meta set for their weapon and then proceed to immediately cart right at the beginning of the hunt :)
With the wealth of models available (open source vs closed, api vs local), I find optimizing the cost-efficiency of your token consumption an important part of business-oriented AI engineering. You don't need "the best" for every task.
Re:LLMs Are Closer to Religion Than They Appear
on Monday June 01, 2026 @08:55AM (#48356209)
When I first heard of "prompt engineering", my first thought was for the Pythia and Roman augurs.
Re:Archaeologists Find Egyptian Mummy Buried with the 'Iliad'
on Thursday May 21, 2026 @08:26AM (#48221537)
I would do unfathomable things for a movie with period-accurate Bronze Age armor sets.
Re:UAE to leave OPEC in blow to oil cartel
on Tuesday April 28, 2026 @11:41AM (#47936064)
The US is more of a bouncer on behalf of Israel than anything else, really.
Re:DeepSeek v4
on Friday April 24, 2026 @03:45AM (#47886972)
I always find it an illuminating experience about the power of mass propaganda every time I see an American believe they somewhat have the moral high ground over China, despite starting a new war somewhere around the globe either for petrol or on behalf of Israel every six months.
Re:OpenAI Livestream: ChatGPT Images 2.0
on Wednesday April 22, 2026 @04:23AM (#47860672)
Maybe they just use Qwen Image under the hood ;p
Re:Qwen3.6-Max-Preview: Smarter, Sharper, Still Evolving
on Tuesday April 21, 2026 @10:26AM (#47849314)
SOTA models war is the new console war.
But more seriously, I can't help but be amused by how emotionally invested in their AI brand of choice people are getting.
Re:Qwen3.6-35B-A3B: Agentic Coding Power, Now Open to All
on Friday April 17, 2026 @05:22AM (#47804015)
My system has 16 Gb VRAM / 32 Gb RAM, and ollama runs qwen3.6:latest at decent speed just fine. The 35b model is a moe, so I guess the whole model is offloaded.
Re:Qwen3.6-35B-A3B: Agentic Coding Power, Now Open to All
on Thursday April 16, 2026 @11:33AM (#47794803)
You can run 25-30b model easily if you use Q3 or Q4 quants and llama-server with a pretty long list of options.
Re:Qwen3.6-35B-A3B: Agentic Coding Power, Now Open to All
on Thursday April 16, 2026 @11:31AM (#47794750)
More like `ollama launch claude --model qwen3.6:latest`
Also you need to check your context size, Ollama default to 4K if <24 Gb of VRAM and you need 64K minimum if you want claude to be able to at least lift a finger.
Re:Paranormasight: A Game Exploring the Depths of Honjo in Tokyo
on Tuesday October 22, 2024 @05:42AM (#41912690)
Some gems like 428 aside, I'm generally not a fan of "pure" VNs (the style is often much too verbose), but VN/puzzle hybrid games like Ace Attorney, 999/VLR or Ghost Trick have slowly established themselves this past decade as one of my favorite genres.
Re:Administrators Have Seized the Ivory Tower
on Sunday December 04, 2022 @06:28PM (#33859225)
Not only the Ivory tower. Every facets of society has been captured by the managerial class.
Re:Do McKinsey and other consultants do anything useful?
on Saturday October 15, 2022 @09:27AM (#33214611)
* Managerialism: The Emergence of a New Ideology
* Mediocracy: The Politics of the Extreme Centre
* The Managerial Revolution
Re:Do McKinsey and other consultants do anything useful?
on Saturday October 15, 2022 @09:22AM (#33214561)
An unavoidable, essential and expensive evolution with the rise (and the domination) of the managerial civilization.
Re:Author Salman Rushdie attacked on lecture stage in New York
on Saturday August 13, 2022 @02:25PM (#32452410)
Words do not bleed.
Re:Author Salman Rushdie attacked on lecture stage in New York
on Saturday August 13, 2022 @01:11PM (#32451785)
Apostasy for ex-Muslims is punishable by death. It makes it much harder to be really a "choice".