Researchers have tricked DeepSeek, the Chinese generative AI (GenAI) that debuted earlier this month to a whirlwind of publicity and user adoption, into revealing the instructions that define how it operates.
pull down to refresh
pull down to refresh
Researchers have tricked DeepSeek, the Chinese generative AI (GenAI) that debuted earlier this month to a whirlwind of publicity and user adoption, into revealing the instructions that define how it operates.
Yea this is pretty conclusive evidence that they exfiltrated data/CoT from ChatGPT. Totally on brand for the chinese (rich, impressive history of being really good at copying). Totally unsurprising imo.
What's more surprsing and interesting is this guy figured out how to seed data on the web to jailbreak ChatGPT and other models: https://x.com/elder_plinius/status/1884332137241014531
Rough understanding that @cmd and I came to:
https://xcancel.com/elder_plinius/status/1884332137241014531
https://off-guardian.org/2025/02/03/the-rise-of-the-immortal-dictator-what-will-ai-mean-for-freedom-and-government/
Does this have anything to do with being open source?
No this is about training data and protections against it containing malicious instructions. The open source part is about how to train, not the data that's fed into training.