Summary:

When stateless LLMs are given memories they will accumulate new beliefs and behaviors, and that may allow their effective alignment to evolve. (Here "memory" is learning during deployment that is persistent beyond a single session.)[1]

LLM agents will have memory: Humans who can't learn new things ("dense anterograde amnesia") are not highly employable for knowledge work. LLM agents that can learn during deployment seem poised to have a large economic advantage. Limited memory systems for agents already exist, so we should expect nontrivial memory abilities improving alongside other capabilities of LLM agents.

Memory changes alignment: It is highly useful to have an agent that can solve novel problems and remember the solutions. Such memory includes useful skills and beliefs like "TPS reports should be filed in the folder ./Reports/TPS". They could also include learning skills for hiding their actions, and beliefs like "LLM agents are a type of [...]

---

Outline:

(01:26) Memory is useful for many tasks

(05:11) Memory systems are ready for agentic use

(09:00) Agents arent ready to direct memory systems

(11:20) Learning new beliefs can functionally change goals and values

(12:43) Value change phenomena in LLMs to date

(14:27) Value crystallization and reflective stability as a result of memory

(15:35) Provisional conclusions

The original text contained 4 footnotes which were omitted from this narration.

---

First published:

Source:

Narrated by TYPE III AUDIO.