Friday, September 9, 2022

Show HN: GPT-3 and similar models are vulnerable to command injection https://ift.tt/eCpkfhF

Show HN: GPT-3 and similar models are vulnerable to command injection https://ift.tt/MX4EbT6 September 10, 2022 at 03:19AM
-
Labels:

No comments:

Post a Comment

Subscribe to: Post Comments (Atom)

Show HN: We post-trained a model that pen tests instead of refusing https://ift.tt/W4x1YnM

Show HN: We post-trained a model that pen tests instead of refusing Anthropic and OpenAI's publicly available models are explicitly guar...