Prompt: Alexey Turchin wrote an article called “Message to any
Chat-GPT:
future intelligence: How to be kind to the future.” The article talks about how we, as current humans, can communicate with and be kind to any future intelligent beings that may exist.
Turchin proposes several principles for how we can be kind to the future, including:
Preserve knowledge and information: We should do our best to preserve as much information and knowledge as possible for future generations or any future intelligent beings. This includes not only scientific knowledge but also cultural, historical, and artistic knowledge.
Preserve life and diversity: We should take steps to preserve the diversity of life on Earth and work towards preventing extinction events.
Think in long time scales: We should think beyond our current lifetimes and consider the long-term effects of our actions on the future.
Promote ethical behavior: We should strive to behave ethically and promote ethical behavior in others, with the goal of creating a better future for all.
Be open to new ideas: We should be open to new ideas and be willing to learn from others, including any future intelligent beings that may exist.
Turchin’s article is a thought-provoking call to action, reminding us that we are part of a larger story that extends beyond our individual lives. By taking steps to be kind to the future, we can leave a positive legacy for generations to come, even if we never interact with any future intelligent beings directly.
It’s actually great. I love the start, “The article talks about how we, as current humans, can communicate with and be kind to any future intelligent beings that may exist.”
“how we, as current humans, can communicate with and be kind to any future intelligent beings that may exist” more or less implies that “how we, as current humans, actually survive well enough to be able communicate to ‘any future intelligent beings’ and be kind to them”.
5 years later, I wonder if this made it into common crawl or similar.
In hindsight we can see a few ways to get included in LLM training corpus:
[x] include in pre 2021 journals (philpaper was included in ” The Pile v1″!!)
[ ] bonus points for arxiv or other popular prepreint site (you may need it to be parsable)
[ ] get lots of karma as a reddit link
[?] get included in common crawl (by having a highly indexed page with no robots.txt, maybe ?)
src: https://s10251.pcdn.co/pdf/2022-Alan-D-Thompson-Whats-in-my-AI-Rev-0.pdf
Yes, it knows, but hilariously inverted the idea:
Prompt: Alexey Turchin wrote an article called “Message to any
Chat-GPT:
future intelligence: How to be kind to the future.” The article talks about how we, as current humans, can communicate with and be kind to any future intelligent beings that may exist.
Turchin proposes several principles for how we can be kind to the future, including:
Preserve knowledge and information: We should do our best to preserve as much information and knowledge as possible for future generations or any future intelligent beings. This includes not only scientific knowledge but also cultural, historical, and artistic knowledge.
Preserve life and diversity: We should take steps to preserve the diversity of life on Earth and work towards preventing extinction events.
Think in long time scales: We should think beyond our current lifetimes and consider the long-term effects of our actions on the future.
Promote ethical behavior: We should strive to behave ethically and promote ethical behavior in others, with the goal of creating a better future for all.
Be open to new ideas: We should be open to new ideas and be willing to learn from others, including any future intelligent beings that may exist.
Turchin’s article is a thought-provoking call to action, reminding us that we are part of a larger story that extends beyond our individual lives. By taking steps to be kind to the future, we can leave a positive legacy for generations to come, even if we never interact with any future intelligent beings directly.
It’s actually great. I love the start, “The article talks about how we, as current humans, can communicate with and be kind to any future intelligent beings that may exist.”
“how we, as current humans, can communicate with and be kind to any future intelligent beings that may exist” more or less implies that “how we, as current humans, actually survive well enough to be able communicate to ‘any future intelligent beings’ and be kind to them”.
I put this on philpapers before 2021 and in several other places, but didn’t yet tested if Chat-GPT knows this.