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)

October 15, 2023

3

[ad_1]

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 …

[ad_2]

Source link

Previous article

“8h30 franceinfo” by Manuel Valls

Next article

“The whore, the ex-prostitute, I accept it’s true but…”

Latest