It looks like it's just for logging, why does it need to block?

Better question - why would you call an LLM (expensive in compute terms) for something that a regex can do (cheap in compute terms)

Regex is going to be something like 10,000 times quicker than the quickest LLM call, multiply that by billions of prompts

▲

orphea 7 hours ago | parent [-]

This is assuming the regex is doing a good job. It is not. Also you can embed a very tiny model if you really want to flag as many negatives as possible (I don't know anthropic's goal with this) - it would be quick and free.

	▲	gf000 6 hours ago \| parent [-]
		I think it's a very reasonable tradeoff, getting 99% of true positives at the fraction of cost (both runtime and engineering). Besides, they probably do a separate analysis on server side either way, so they can check a true positive to false positive ratio.