Hippocampus vs AI - LLMs Can't Do What You Can
summary
Comparison between human memory (hippocampus) and large language models, arguing that LLMs cannot replicate certain human cognitive abilities. Discusses limitations of current AI architectures and highlights tasks where biological memory and understanding outperform LLMs.
AI-written summary · about
chapters (8)
- 0:00Introduction
- 2:37Decision-making problems
- 15:40Expert thinking
- 20:17Hippocampus in learning
- 27:43Problem/solution archetypes
- 33:43Selling solutions
- 37:35Taxi booking example
- 40:46Summary
related talks
46mThe Anatomy of Memory in Humans and AI Agents
17mPsychology of AI
44mUnderstanding the abilities of AI systems: Memorization, generalization, and points in between
23mGhost in the Machine: AI, Spirituality and a New Humanism
41mEnhancing LLMs with Graph Technology
25mWhat does it take to build long-term state for AI agents?
49mA Practical Approach to Using LLMs: Peculiarities and Pitfalls
54mAI in Testing: Hip or Hype?