A history correction:
I am not the first to discover prompt injection. I was merely the first to do so and discuss it publicly.
PI was discovered independently by multiple teams. The first was Preamble, an LLM security company, whose find predates mine by several months.
I am not the first to discover prompt injection. I was merely the first to do so and discuss it publicly.
PI was discovered independently by multiple teams. The first was Preamble, an LLM security company, whose find predates mine by several months.
I tweeted about prompt injection within minutes of finding it, only because I failed to appreciate its severity — I thought I was posting a PSA on the importance of quoting user input.
Had I understood, I would have disclosed more responsibly.
Had I understood, I would have disclosed more responsibly.
For context, my original “Haha pwned!!” tweet, publicly disclosing prompt injection for the first time:
https://twitter.com/goodside/status/1569128808308957185
To clarify, I don’t know for sure that Preamble was the first, and I don’t think they claim to be — but they’ve published a redacted copy of their disclosure to OpenAI dated May 3, 2022. It’s possible that OpenAI was aware of it earlier.
• • •
Missing some Tweet in this thread? You can try to
force a refresh
