Thomas Claburn / The Register:

Researchers find that a modest amount of fine-tuning can undo safety efforts that aim to prevent LLMs such as OpenAI's 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 amount of fine-tuning can undo safety efforts that aim to prevent LLMs such as OpenAI's 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