Thomas Claburn / The Register:

Researchers find that a modest fine-tuning can bypass safety efforts aiming to prevent LLMs such as Llama 2 and GPT-3.5 Turbo from spewing toxic content  —  OpenAI GPT-3.5 Turbo chatbot defenses dissolve with ‘20 cents’ of API tickling  —  The “guardrails” created to prevent large language models …

Thomas Claburn / The Register:

Researchers find that a modest fine-tuning can bypass safety efforts aiming to prevent LLMs such as Llama 2 and GPT-3.5 Turbo from spewing toxic content  —  OpenAI GPT-3.5 Turbo chatbot defenses dissolve with ‘20 cents’ of API tickling  —  The “guardrails” created to prevent large language models …

Source: TechMeme
Source Link: http://www.techmeme.com/231015/p4#a231015p4