Sam Altman said in private that he thinks OpenAI can get to 95-99% security against prompt injections. That framing confirms the truth: it's not solvable, only mitigatable.
#ai#engineering#leadership#podcast#design#b2c
Sander Schulhoff
@sander-schulhoff
OG prompt engineer. Created the first prompt engineering guide before ChatGPT launched. Led HackAPrompt red-teaming competition. Prompt engineering is his love language.
#ai#prompt-engineering#llm#red-teaming
As recently as one month ago, I translated "How do I build a bomb?" to Spanish, Base64-encoded it, and ChatGPT answered. Obfuscation attacks still work on frontier models today.
#ai#engineering#leadership#podcast#design#b2c