Post Content
Can LLMs reason or they are just stochastic parrots which can only generate answers based on its training data. In this video, I test Google’s new chatbot model, Gemini Experimental 1114, which currently tops the chatbot arena leaderboard. Using a set of modified thought experiments and puzzles, I explore whether this model can truly reason or if it’s mainly relying on pattern recognition.
LINKS:
https://github.com/cpldcpu/MisguidedAttention
💻 RAG Beyond Basics Course:
https://prompt-s-site.thinkific.com/courses/rag
Let’s Connect:
🦾 Discord: https://discord.com/invite/t4eYQRUcXB
☕ Buy me a Coffee: https://ko-fi.com/promptengineering
|🔴 Patreon: https://www.patreon.com/PromptEngineering
💼Consulting: https://calendly.com/engineerprompt/consulting-call
📧 Business Contact: engineerprompt@gmail.com
Become Member: http://tinyurl.com/y5h28s6h
💻 Pre-configured localGPT VM: https://bit.ly/localGPT (use Code: PromptEngineering for 50% off).
Signup for Newsletter, localgpt:
https://tally.so/r/3y9bb0
00:00 Introduction to Gemini Experimental 1114
00:30 Testing Reasoning with Misguided Attention Prompts
02:00 Modified Trolley Problem
04:21 Barber Paradox Challenge
06:34 Schrodinger’s Cat Variation
08:38 Monty Hall Problem Twist
11:23 River Crossing Puzzle
14:24 What does this mean?
All Interesting Videos:
Everything LangChain: https://www.youtube.com/playlist?list=PLVEEucA9MYhOu89CX8H3MBZqayTbcCTMr
Everything LLM: https://youtube.com/playlist?list=PLVEEucA9MYhNF5-zeb4Iw2Nl1OKTH-Txw
Everything Midjourney: https://youtube.com/playlist?list=PLVEEucA9MYhMdrdHZtFeEebl20LPkaSmw
AI Image Generation: https://youtube.com/playlist?list=PLVEEucA9MYhPVgYazU5hx6emMXtargd4z Read More Prompt Engineering
#Promptengineering #AI