80% of hateful tweets remain online after five months with no higher removal rate than non-hateful content, while human-AI moderation pipelines can feasibly cut user exposure below regulatory penalty costs.
I missed this one: Someone did get a prompt leak attack to work against the bot, Sep 2022
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
representative citing papers
PromptInject shows that simple adversarial prompts can cause goal hijacking and prompt leaking in GPT-3, exploiting its stochastic behavior.
citing papers explorer
-
The Enforcement and Feasibility of Hate Speech Moderation on Twitter
80% of hateful tweets remain online after five months with no higher removal rate than non-hateful content, while human-AI moderation pipelines can feasibly cut user exposure below regulatory penalty costs.
-
Ignore Previous Prompt: Attack Techniques For Language Models
PromptInject shows that simple adversarial prompts can cause goal hijacking and prompt leaking in GPT-3, exploiting its stochastic behavior.