How we fixed prompt injection for all models on Fireworks(fireworks.ai)
fireworks.ai
How we fixed prompt injection for all models on Fireworks
https://fireworks.ai/blog/safe-tokenization-preventing-prompt-injection-on-fireworks
1 comments
It feels a bit SQL injection all over again tbh. This should have probably been the standard from the beginning. Way more elegant than counter prompts and guardrails