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 (Thomas Claburn/The Register)

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 …

from Techmeme https://ift.tt/8qSI0un