Current work in AI alignment | Paul Christiano | EA Global: San Francisco 2019
Вставка
- Опубліковано 15 тра 2024
- Paul Christiano, a researcher at OpenAI, discusses the current state of research on aligning AI with human values: what’s happening now, what needs to happen, and how people can help. This talk covers a broad set of subgoals within alignment research, from inferring human preferences to verifying the properties of advanced systems. To learn more about effective altruism, visit effectivealtruism.org
This talk was filmed at EA Global: San Francisco 2019. You can learn more about these conferences at eaglobal.org
You can read a transcript, or discuss this talk, on the Effective Altruism Forum: forum.effectivealtruism.org/p...
Paul thinks quickly and this talk was super fast. I found myself pausing multiple times.
The talk was clear and incisive (particularly for the first five golden headings), and it is useful for gaining a 'big picture' view.
Awesome to see a topology overview for the first time. Thank you! I found this because I was reading the alignment problem
Perfect at 0.75x speed
good talk. would be even better if it had more examples.
Hello EA,
Sorry to bother you. Can I ask for your permission to reupload (repost) your videos to a Chinese video platform called Bilibili? Since UA-cam is banned in China, it is quite hard for people to watch UA-cam (using VPN), not to mention that a lot of Chinese people cannot speak fluent English. There are tons of fans in China wanting to learn from this topic, and I'm certain that many people will like your videos. I will make sure to ALWAYS include your channel's name, video link, and credit you as the original author in the video description. Anyway, I'm looking forward to your new videos and have a good day!
Thank you
Alin
As a reminder for everyone, speaking quickly has nothing to do with the quality of your reasoning. The two variables are decorrelated. You can speak quickly and say lots of bullshits. The speed the way you talk will only determine the quantity of words.
That is not an argument. If you disagree with what the speaker is saying, you need to give an actual reason.