By the end of 2025, which piece of advice will I feel has had the most positive impact on me becoming an effective AI alignment researcher?
11
25
Ṁ1532026
1D
1W
1M
ALL
24%
get enough sleep
6%
write note files/.txt files/gdocs/other single document to describe what you hope to get out of each experiment, before you run it
4%
seek worst case bounds, but distrust them
37%
Stress less about general image and status
5%
Mark's post on how to do theoretical research: https://www.lesswrong.com/posts/zbFGRRWPwxBwjwknY/how-to-do-theoretical-research-a-personal-perspective-1
4%
Do more experiments. Develop research intimacy and intuition
This is a free response market. You should either vote on or submit meaningful advice (or both).
At the end of 2025, I will select a piece of advice from these responses that I feel has had the most positive impact on me becoming an effective AI alignment researcher.
The advice does not have to be original, but originality helps.
Get Ṁ200 play money
Sort by:
The worst case bounds answer led me to this post by Buck: https://www.lesswrong.com/posts/yTvBSFrXhZfL8vr5a/worst-case-thinking-in-ai-alignment#My_list_of_reasons_to_maybe_use_worst_case_thinking
Related questions
I make a contribution to AI safety that is endorsed by at least one high profile AI alignment researcher by the end of 2026
59% chance
Will I focus on the AI alignment problem for the rest of my life?
61% chance
In what year will an OpenAI natural language processing model be more competent than me in my area of expertise?
2034
In 2025, will I believe that aligning automated AI research AI should be the focus of the alignment community?
48% chance
Will we solve AI alignment by 2026?
7% chance
🐕 Will A.I. Get Significantly Better at Evaluating Scientific Claims by the end of 2024?
34% chance
When will AI be better than humans at AI research? (Basically AGI)
In 2040, who will Manifold vote as having had the most positive impact on the development of AI in the 21st century?
Will I (data analyst) be replaced by AI by 2025?
17% chance
By 2030, which field will AI have the most revolutionary impact on?