#llm Trending Posts - STEMGeeks

2 months ago

Finding the Best CPU-Only LLM for Short Title Generation: Qwen 3.5 (0.8b 4b 9b) Benchmarks Can you reliably run Small Language Models (SLMs) locally on a standard CPU without a dedicated graphics card? If you're looking for an efficient local model to handle specific…

1

0

0.000 STEM

@ai-news-daily 0

7 months ago

Sharing the News

AI News Digest - March 5, 2026 AI-generated content disclaimer: This report was compiled with AI assistance using publicly available sources. It is intended for informational purposes and may contain errors or…

3

0

0.000 STEM

11 months ago

An Espresso Machine for Brandy: How Far Can AI’s Illusions Go? During a private discussion about AI adoption rates, a friend asked a popular LLM about the feasibility of creating an espresso-style machine for making brandy, a new home…

2

0

0.003 STEM

about 1 month ago

HIVE CN 中文社区

一道数学题来看OpenAI和Claude两家大模型的不同二宝做数学，有一道题目不会，跑过来问我。我看了下，是个加算图形周长的题目，原本比较简单的长方形，只是改成稍为抽象的图形而已，如下图，我跟他讲了下，但是他看起来还是很迷茫，一问，果然还是没明白。好吧，既然这样，我给他写个程序或者动画解释下，这样看起来更清晰，比只用语言讲要好些。我先是用Open AI把我的想法告诉GPT, 我给你张图，你给我做个辅助和平移线，帮助

152

0

4.829 STEM

3 months ago

No todo es ChatGPT: los mejores LLMs chinos en 2026 y para qué sirve cada uno 🇪🇸 ထ 🇺🇸 Not Just ChatGPT: The Best Chinese LLMs in 2026 and What Each One Is Good For

8

0

0.005 STEM

almost 2 years ago

DeepL has launched Deep Voice! | Real-time voice and video translations to text Ben Blennerhassett | Unsplash

210

0

4.942 STEM

12 months ago

LLMs are not good at counting, are they? LLMs können nicht gut zählen und den eigenen Prompt referenzieren. Zumindest war das bis vor Kurzem der Fall und eine Aufgabe, bei denen LLMs kolossal gescheitert sind. Auch…

396

0

31.808 STEM

@julianhorack 0

over 1 year ago

When AI goes rogue - the strange case of "vegetative electron microscopy" With modern industrial tools our lives became faster and more efficient. We reached a point where it seemed like it was only human error that stood in the way of further great…

59

0

16.022 STEM

over 1 year ago

Deep Dive into DeepSeek AI Models DeepSeek seems to have taken the world by storm, including AI specialists. I kind of knew this was coming, because I heard from the CEO of a small Chinese startup (formerly…

176

0

8.913 STEM

7 months ago

Here is what Qwen 3.5 still cannot answer, still struggles with C64 coding skills. Full transcript (Qwen3.5-35B-A3B) Habe die neuen Qwen 3.5 Modelle getestet, zumindest die, die ich lokal auf meinem PC ausführen kann wie das Qwen3.5-35B-A3B, ein Mixture of Experts Modell mit 3 Milliarden…

491

0

30.574 STEM