ChatGPT and Claude, two AI models one built by OpenAI and one by Anthropic, take very different approaches to their models.

One of the big points of divergence is in persistent memory.

Claude starts each chat from zero. ChatGPT has persistent memory.

What are the pros and cons for persistent memory?

Pros:

• Better outcomes, I can relax to write more like me and it does.
• More convenient for the user. I don’t have to Rez plain a complex situations.

Cons:

• All user interaction could be exposed at once.
• Hard to delete information or start from zero once it’s in the system.
• System develops biases.
• Asymmetric relationship, AI remembers everything human doesn’t.