WHAT? Qwen3.6-A3B Could Solve This?

Discover AI · Beginner ·📄 Research Papers Explained ·3w ago
Can the new Qwen 3.6 MoE with 35B parameter (active only 3B) solve my classical causal reasoning test? MY elevator test? A new experiment with active steering of the reasoning complexity of a tiny A3B model. Youtube playlist here https://www.youtube.com/playlist?list=PLgy71-0-2-F0Rla8lu5ZldpYQUfXM_5bT 00:00 An experiment w/ Qwen 3.6 35B A3B 01:30 Analyse Reasoning Patterns 06:05 Live test on Alibaba cloud 09:31 First result by Qwen3.6 35B A3B 10:28 Explain alternative Routes 12:49 Optimize your Solution 15:03 Validate your Result 16:50 Analyse your Strategy #airesearch #aiexplained #tinyai #qwen #aireasoning #steering #scienceexplained
Watch on YouTube ↗ (saves to browser)
Sign in to unlock AI tutor explanation · ⚡30

Related AI Lessons

The ABCs of reading medical research and review papers these days
Learn to critically evaluate medical research papers by accepting nothing at face value, believing no one blindly, and checking everything
Medium · LLM
#1 DevLog Meta-research: I Got Tired of Tab Chaos While Reading Research Papers.
Learn to manage research paper tabs efficiently and apply meta-research techniques to improve productivity
Dev.to AI
How to Set Up a Karpathy-Style Wiki for Your Research Field
Learn to set up a Karpathy-style wiki for your research field to organize and share knowledge effectively
Medium · AI
The Non-Optimality of Scientific Knowledge: Path Dependence, Lock-In, and The Local Minimum Trap
Scientific knowledge may be stuck in a local minimum, hindering optimal progress, and understanding this concept is crucial for advancing research
ArXiv cs.AI

Chapters (8)

An experiment w/ Qwen 3.6 35B A3B
1:30 Analyse Reasoning Patterns
6:05 Live test on Alibaba cloud
9:31 First result by Qwen3.6 35B A3B
10:28 Explain alternative Routes
12:49 Optimize your Solution
15:03 Validate your Result
16:50 Analyse your Strategy
Up next
Microsoft Research Forum | Season 2, Episode 4
Microsoft Research
Watch →