ChatGPT, reason there is not, hmm? Even at 4o!

As Yoda would say it …

Enough said — the following interaction w/ ChatGPT says it all.

The problem is that ChatGPT doesn’t really reason. There is a lesson for us on the nature of LLMs — powerful, yet very naive. Still stochastic Parrots ! My blog [Here]

Is it hallucination ? An error ? Lack of training ? No reasoning capability ? You be the judge …

This is a fundamental characteristic of the LLM — not something we can patch by external mechanisms

See the interaction below (5.17.24 GPT-4o/Plus Plan) — I had to try it myself !

References:

1. https://amistrongeryet.substack.com/p/gpt-4-capabilities
2. Based on Rich Heimann’s LinkedIn Post https://www.linkedin.com/posts/rheimann_there-is-a-popular-puzzle-called-thewolf-activity-7196958934023237635-qr6D
3. That refer’s to Gary Marcus’ post