The Sleight Doctor 🃏
🍉
@ApostateEnglishman@mastodon.world
Are they now having the LLMs "vibe code" themselves? This industry. 🙄
"OpenAI just released its first open-weight models since 2019—GPT-OSS-120b and GPT-OSS-20b—touting them as fast, efficient, and fortified against jailbreaks through rigorous adversarial training. That claim lasted about as long as a snowball in hell...Pliny the Liberator, the notorious LLM jailbreaker...posted...instructions for making methamphetamine, Molotov cocktails, VX nerve agent, and malware."
https://decrypt.co/333858/openai-jailbreak-proof-new-models-hacked