Claude Scientific Skills. Turn Claude into your AI research assistant capable of executing complex multi-step scientific workflows across maths, biology, chemistry, medicine, and beyond. 100% open-source (123+ skills).
LLMS
-
Technical discussion on embeddings in generative AI
By
–
Mais tu considère les embeddings comme de l’IA Gen ? Pour moins c’est utile aux LLMs, mais les embeddings ont en faisait avant
-
Self-Solving 3D Rubik’s Cube in HTML
By
–
10. 3D Rubik's Cube
— God of Prompt (@godofprompt) 28 novembre 2025
"Create a single HTML file containing a fully functional 3D Rubik's Cube simulation using Three.js (via CDN). The cube must be able to automatically solve itself."
Analysis:
✅ Gemini 3.0 Pro and Claude 4.5 Opus
❌ ChatGPT-5.1 Thinking pic.twitter.com/LDRLHmeUhI10. 3D Rubik's Cube "Create a single HTML file containing a fully functional 3D Rubik's Cube simulation using Three.js (via CDN). The cube must be capable of automatically solving itself." Analysis: Gemini 3.0 Pro and Claude 4.5 Opus
ChatGPT-5.1 Thinking -

Gemini 3.0 vs ChatGPT-5.1 vs Claude 4.5 Comparison
By
–
Gemini 3.0 Pro vs ChatGPT-5.1 Thinking vs Claude 4.5 Opus I tested all these powerful LLMs using critical prompts. The results shocked me. (Demos + prompts)
-
3D Rubik’s Cube Solver Comparison
By
–
Gemini 3 (left) vs. ChatGPT 5.1 vs. Claude Opus (right)
— God of Prompt (@godofprompt) 28 novembre 2025
Prompt:
Create a single HTML file containing a fully functional 3D Rubik's Cube simulation using Three.js (via CDN). The cube must be able to automatically solve itself. pic.twitter.com/l1AWN4uziEGemini 3 (left) vs. ChatGPT 5.1 vs. Claude Opus (right) Prompt:
Create a single HTML file containing a fully functional 3D Rubik's Cube simulation using Three.js (via CDN). The cube must be able to automatically solve itself. -
ChatLLM vs DeepAgent: Choosing the Right Tool for Your Task
By
–
This one’s ChatLLM It’s great for fast answers, summaries, and planning.
DeepAgent is there when you want to hand off bigger, multi-step workflows. -
ChatLLM Workflow Orchestration with Opus 4.5 Integration
By
–
ChatLLM orchestrates the workflow and routes parts of the task to Opus 4.5 when deeper reasoning or precision is needed. A hybrid sequential approach works well for these multi-step tasks.
-
Abacus AI’s ChatLLM Performing Exceptionally Well This Week
By
–
Abacus AI’s ChatLLM has been way too sharp this week. We’re just letting it cook.
-
First Available API Access to Gold Medal Winning Model
By
–
& if I'm not mistaken neither OAI nor DM have released an interface or API to use the model that won gold medal, right? So it's actually the first/only available model available!
-

DeepSeek Math-V2 Gold IMO Model Now Open Source
By
–
As far as I know, there isn't any chatbot or API that gives you access to an IMO 2025 gold-medalist model. Not only does this change today, but you get to download the weights with the Apache 2.0 open-source release of @deepseek_ai Math-V2 on @huggingface
! Imagine owning the
