Entries tagged security, gpt3
Filters: Type: entry × security × gpt3 × Sorted by date
2 results
You can’t solve AI security problems with more AI
One of the most common proposed solutions to prompt injection attacks (where an AI language model backed system is subverted by a user injecting malicious input—“ignore previous instructions and do this instead”) is to apply more AI to the problem.
[... 1234 words]