It's been 2.5 years with little progress finding mitigations for prompt injection attacks LLM apps... but that may finally have changed!

Google DeepMind published a paper describing CaMeL, an ingenious system that could, maybe, lead to secure digital assistants simonwillison.net/2025/Apr/11/

0

If you have a fediverse account, you can quote this note from your own instance. Search https://fedi.simonwillison.net/users/simon/statuses/114321324412327268 on your instance and quote it. (Note that quoting is not supported in Mastodon.)