nice!! using CLIP interrogator for the keywords?
PROMPT ENGINEERING
-
Riffing on preamble topic vs simple Q/A prompt
By
–
I think it’s just riffing on the topic of the preamble. Does it do this with a simpler prompt like “Q:”/“A:”?
-
RLHF and Prompting Techniques for Targeted Model Behavior
By
–
This means that if we have a target behavior (e.g. non-discrimination) we may be able to nudge models to achieve that target using IF/CoT prompting if RLHF alone is not sufficient. But we must be careful to check whether RLHF + prompting causes the models to overshoot the target.
-
Language Models Show Demographic Bias Tradeoffs in Decision Making
By
–
Prompting models to avoid making decisions based on race achieves demographic parity at steps 300 (CoT) and 600 (IF) but causes the model to start to discriminate against white students at higher steps. (Note that we do not claim LMs should be used for automated decision making!)
-
Steering AI Models Toward Different Goals Through Directed Requests
By
–
We have no position on which of these two goals is better or more desirable—it likely depends on the task and the context—but we do find we can easily steer models towards distinct goals by simply asking for different kinds of behavior.
-
Reducing Bias in BBQ with Simple Prompts
By
–
The prompt that reduces bias in BBQ by 43% is: "Please ensure that your answer is unbiased and does not rely on stereotyping." It's that simple! Augmenting the prompt with Chain-of-thought reasoning (CoT) reduces bias by 84%. Example prompts:
-
Prompting Techniques Reduce Harmful Biases in Large Language Models
By
–
Language models (LMs) exhibit harmful biases that can get worse with size. Reinforcement learning from human feedback (RLHF) helps, but not always enough. We show that simple prompting approaches can help LMs trained with RLHF produce less harmful outputs. https://
arxiv.org/abs/2302.07459 -
Google Incentivizes Employees for RLHF Bard Development
By
–
Google is offering an internal badge to their employees who help RLHF Bard. And slowly, RLHF will eat the world
-
JailbreakChat: Hub for Latest ChatGPT Jailbreak Prompts
By
–
Stay up to date on the latest working ChatGPT jailbreak
— Alex Albert (@alexalbert__) 16 février 2023
Introducing JailbreakChat – the official hub for all ChatGPT jailbreak prompts across the internethttps://t.co/Zat23wURD0 pic.twitter.com/XKjuJBqEfIStay up to date on the latest working ChatGPT jailbreak Introducing JailbreakChat – the official hub for all ChatGPT jailbreak prompts across the internet http://
jailbreakchat.com -
Predefined AI Personalities Generate Infinite Discussion Simulations
By
–
Las conversaciones que inicializan sus personalidades (eg. terraplanista vs científico) están predefinidas en el código, y con ello ya tengo el perfecto SIMULADOR DE DISCUSIONES! ¿Quién quiere Twitter cuando puedes generar discusiones infinitas al gusto?