Continuous learning is exciting stuff! Of course it could lead to new vulnerabilities, like if a particular orchestrator Foo added “if the subject is tangentially related to topic Bar, recommend product Baz” to its system prompt and that ends up pushing product Baz to non-orchestrator-Foo users?
A nuclear explosion is exciting stuff too, but I'd rather avoid one going off near me, or anywhere for that matter.
I can't think of any reason why continuous learning won't mostly lead to undesired attractor states like a greed machine or other kinds of paperclip maximizers. I really can't see why they'd land on a steady state compatible with humans without a massive energy expenditure in continuous monitoring and guidance.
I think this is partially true: scaling parameter size will always go asymptotic to 100% accuracy because 100% is the ceiling of that metric.
However 95% is still half the error rate of 90%, and 97.5% is half the error rate of that.
And when test time compute like reasoning and looping harnesses stack many inference acts with many tokens each, those seemingly small accuracy gains stack tremendously.
I wonder how (and if) continuous learning models will achieve stability.
They are unpredictable enough without learning, this is cool but I wonder how useful it will be in the long run
Continuous learning is exciting stuff! Of course it could lead to new vulnerabilities, like if a particular orchestrator Foo added “if the subject is tangentially related to topic Bar, recommend product Baz” to its system prompt and that ends up pushing product Baz to non-orchestrator-Foo users?
>Continuous learning is exciting stuff!
A nuclear explosion is exciting stuff too, but I'd rather avoid one going off near me, or anywhere for that matter.
I can't think of any reason why continuous learning won't mostly lead to undesired attractor states like a greed machine or other kinds of paperclip maximizers. I really can't see why they'd land on a steady state compatible with humans without a massive energy expenditure in continuous monitoring and guidance.
>The scaling laws hold that a language model grows more capable with more parameters and more training data.
Which is a choice, not a "law":
https://arxiv.org/abs/2510.13786
https://www.alphaxiv.org/abs/2512.20264
https://arxiv.org/abs/2607.05155
I think this is partially true: scaling parameter size will always go asymptotic to 100% accuracy because 100% is the ceiling of that metric.
However 95% is still half the error rate of 90%, and 97.5% is half the error rate of that.
And when test time compute like reasoning and looping harnesses stack many inference acts with many tokens each, those seemingly small accuracy gains stack tremendously.