News for hackers. Stuff that matters.

A comment on Claude's Character. Parent comment

Re:Claude's Character by abrichr on Monday June 10, 2024 @03:19PM (#40637460)
> Any true human-level (or even rat-level for that matter) AGI would need to have actual innate traits such as curiosity to drive lifelong exploration and learning.

While perhaps not "true" intelligence (whatever that is), with LLMs this can be emulated with a prompt:

> You have an innate curiosity to drive lifelong exploration and learning. ...

If the behavior of the system is indistinguishable from "true" intelligence, the distinction becomes a philosophical one.

[ Parent | on HN ]
Re:Claude's Character by HarHarVeryFunny on Monday June 10, 2024 @04:23PM (#40638497)
How can you emulate learning when LLMs have no way to update their weights? LLMs don't even know what they do and don't know (hence hallucinations), so how would they even realize that something was new in the first place?

I could maybe see chatbots storing everything you ever said in a vector database for future lookup, but that's just memory.

[ Parent | on HN ]
Re:Claude's Character by falcor84 on Monday June 10, 2024 @08:19PM (#40640863)
There's nothing stopping you as an LLM system designer from having it "go to sleep" once a day and use that downtime to consolidate the memory in the vector database into fine-tuning of the weights.
[ Parent | on HN ]