You don’t want to do that for anything you want to be able to vary, but they do something similar with a “soul document” for things they always want to apply.

https://news.ycombinator.com/item?id=46125184

▲

supriyo-biswas 6 hours ago | parent | next [-]

In this token-mania frenzy that has taken hold of the industry, I guess solutions like "soul document" and "system prompts" will continue for a while, and once the industry matures a bit we'll go back to things like LoRA[1] and control vectors[2][3].

The other explanation may be that these AI labs may be expecting more government scrutiny, and "here's a document" would probably go better than "here's some vector representation of our values" when talking to politicians.

[1] https://arxiv.org/abs/2106.09685

[2] https://vgel.me/posts/representation-engineering/

[3] https://transformer-circuits.pub/2024/scaling-monosemanticit...

	▲	monkpit 4 hours ago \| parent [-]
		Is there a reason a document could not be converted to vectors via embedding, and you’d have both? EDIT: I see, the control vectors operate more directly upon the model, in a way embedding vectors don’t quite have access to.

▲

energy123 6 hours ago | parent | prev [-]

If it's a fine tuning step at the end, why is the need for it to vary a problem? Can't you run the fine tuning, test for regression, and deploy the weights in a day?

I think the more likely reason is it doesn't work as well as in context learning. Otherwise they would prefer to avoid polluting context and degrading performance.

	▲	TZubiri 6 hours ago \| parent [-]
		Fine tuning isn't the same and doesn't have the same effect as selecting input tokens. Does there exist a model X that behaves exactly as a model Y with context Z? Maybe, but it's not trivial to achieve and might possibly be convoluted and more expensive.