Yes, it’s a great topic. The aspect which seems to be missing from “AI capabilities can be significantly improved without expensive retraining”, https://arxiv.org/abs/2312.07413 is that post-training is a particularly fertile ground for rapid turnaround self-modification and recursive self-improvement, as post-training tends to be rather lightweight and usually does not include a delay of training a novel large model.
Some recent capability works in that direction include, for example
People who are specifically concerned with rapid foom risks might want to focus on this aspect of the situation. These self-improvement methods currently saturate in a reasonably safe zone, but they are getting stronger both due to novel research, and due to improvements of the underlying LLMs they tend to rely upon.
Yes, it’s a great topic. The aspect which seems to be missing from “AI capabilities can be significantly improved without expensive retraining”, https://arxiv.org/abs/2312.07413 is that post-training is a particularly fertile ground for rapid turnaround self-modification and recursive self-improvement, as post-training tends to be rather lightweight and usually does not include a delay of training a novel large model.
Some recent capability works in that direction include, for example
“Self-Taught Optimizer (STOP): Recursively Self-Improving Code Generation”, https://arxiv.org/abs/2310.02304
“Language Agents as Optimizable Graphs”, https://arxiv.org/abs/2402.16823
People who are specifically concerned with rapid foom risks might want to focus on this aspect of the situation. These self-improvement methods currently saturate in a reasonably safe zone, but they are getting stronger both due to novel research, and due to improvements of the underlying LLMs they tend to rely upon.