Watch this week’s episode on YouTube or listen to the audio version here. This week, we see how to break ChatGPT, how to integrate diverse opinions in an AI and look at a bunch of the most interesting papers from the ML safety workshop happening right now! ChatGPT jailbreaks Last...
Listen to this week’s update on YouTube or podcast. This week, we’re looking at the wild abilities of ChatGPT, exciting articles coming out of the NeurIPS conference and AGI regulation at the EU level. My name is Esben and welcome to week 48 of updates for the field of ML...
TLDR; no one talks about how far we are towards safe AGI and the focus is on when AGI doom arrives. We want to readjust this focus and measure progress, guide and facilitate research, and evaluate projects in AI safety for impact. We also ask you to add your views...
Watch this week’s episode on YouTube or listen to the audio version here.
This week, we see how to break ChatGPT, how to integrate diverse opinions in an AI and look at a bunch of the most interesting papers from the ML safety workshop happening right now!
Last week, we reported that ChatGPT has been released along with text-davinci-003. In the first five days, it received over a million users, a product growth not seen in a long time. And if that wasn’t enough, OpenAI also released WhisperV2 that presents a major improvement to voice recognition.
However, all is not safe with ChatGPT! If you have been browsing Twitter, you’ll have seen the hundreds of users... (read 1172 more words →)
Listen to this week’s update on YouTube or podcast.
This week, we’re looking at the wild abilities of ChatGPT, exciting articles coming out of the NeurIPS conference and AGI regulation at the EU level.
My name is Esben and welcome to week 48 of updates for the field of ML & AI safety. Strap in!
Just two days ago, ChatGPT was released and it is being described as GPT-3.5. We see many bug fixes from previous releases and it is an extremely capable system.
We can already now see it find loopholes in crypto contracts, explain and solve bugs, replace Google search and most importantly, show capability to deceive and circumvent human oversight!
Despite being significantly safer than the previous version (text-davinci-002),... (read 1155 more words →)
TLDR; no one talks about how far we are towards safe AGI and the focus is on when AGI doom arrives. We want to readjust this focus and measure progress, guide and facilitate research, and evaluate projects in AI safety for impact. We also ask you to add your views to this survey.
It was a hot London Summer day and fourteen people had gathered to discuss the future of AI safety. To ascertain the mission criticality of our endeavor, we drew everyone’s AGI timelines on a whiteboard. The product of our estimates was close to the Metaculus estimate and some expressed concern at the stress of impending doom.
We then proceeded to draw our... (read 1790 more words →)