|
|
|
|
|
|
by cadence-
814 days ago
|
|
|
It probably exists, but not very well known, or is too expensive to use. For example, I wrote a SpamAssassin extension that adds some score to messages based on whether LLM thinks it is a spam email. It worsk very well, but it's a bit pricey when it comes to API costs. Maybe if I switch it from GPT3.5 to Claude Haiku it will make more sense. I think we still need to see prices of LLM tokens go significantly down and performance increase before such web filtering solutions make sense. The Claude Haiku is a big step int he right direction, but the price is still high for this kind of high-volume usage. |
|
|