←back to thread

684 points prettyblocks | 2 comments | | HN request time: 1.38s | source

I mean anything in the 0.5B-3B range that's available on Ollama (for example). Have you built any cool tooling that uses these models as part of your work flow?
1. eb0la ◴[] No.42785183[source]
We're using small language models to detect prompt injection. Not too cool, but at least we can publish some AI-related stuff on the internet without a huge bill.
replies(1): >>42785713 #
2. sitkack ◴[] No.42785713[source]
What kind of prompt injection attacks do you filter out? Have you tested with a prompt tuning framework?