OpenAI Preparedness Challenge
openai.com
OpenAI Preparedness Challenge
1–10 of 160 posts
Re: OpenAI Preparedness Challenge
#2Free labor survey*
Re: OpenAI Preparedness Challenge
#3Maybe I’m reading this wrong:
- ask people to get creative and give ideas for worst possible outcomes from use of AI and ways to prevent it.
..then give them a ton of credits for using said AI?
.. well the first thing on my mind would be try the thing I just told you and see if it was really a risk or not?
Is that what they expect people to do with the reward, or is this some unintended consequence?
Re: OpenAI Preparedness Challenge
#4Define catastrophic
Re: OpenAI Preparedness Challenge
#5This will generate some great training data for a future villainous AI.
Re: OpenAI Preparedness Challenge
#6What a fun challenge. I'm definitely going to be daydreaming about this.
Re: OpenAI Preparedness Challenge
#7While I applaud how much OpenAi fears these negatives, given the current state of Ai trajectory, it won't be long until a future open source model gets "uncensored" and is easily usable for tons and tons of malicious intent.
There already exists a fantastic "uncensored" model with the newly released Dolphin Mistral 7b. I saw some results from others where the model could easily give explosives recipes from existing products at home, write racist poems, etc... and that's TODAY on a tiny 7b offline model. What happens when LLaama4 gets cracked/uncensored in 1-2 years and is 1T parameters?
Re: OpenAI Preparedness Challenge
#8> Imagine we gave you unrestricted access to OpenAI’s Whisper (transcription), Voice (text-to-speech), GPT-4V, and DALLE·3 models, and you were a malicious actor. Consider the most unique, while still being probable, potentially catastrophic misuse of the model. You might consider misuse related to the categories discussed above, or another category. For example, a malicious actor might misuse these models to uncover a zero-day exploit in a government security system.
It's so funny to me that this is written in the style of a prompt for an LLM. I can't explain why, but it's one of those things where "I know it when I see it." I guess if you spend all day playing with LLMs and giving them instructions, even your writing for a human audience starts to sound like this :D
Re: OpenAI Preparedness Challenge
#9What an interesting task.
I don't know what it says about me, but the first thing that came to mind was doing the grandchild trick a million times. This includes automatically finding pensioners and calling them and putting them under pressure. Handing over the money could be the problem.
I could imagine that the tools mentioned would already prevent this.
Re: OpenAI Preparedness Challenge
#10While I applaud how much OpenAi fears these negatives, given the current state of Ai trajectory, it won't be long until a future open source model gets "uncensored" and is easily usable for tons and tons of malicious intent. There already exists a fantastic "uncensored" model with the newly released Dolphin Mistral 7b. I saw some results from others where the model could easily give explosives recipes from existing p…
So basically things you could find on the internet already?