The following is a nitpick on an 18 year old blog post. This fable is retold a lot. The progenitor of it as a rationalist mashal is probably Yudkowsky's classic sequence article. To adversarially summarize: 1. It's the beginning of the second world war. The evil governor of California wishes...
The standard argument usually goes something like this: > Alice: there's a lot about the Earth that seems suspiciously fine-tuned for the evolution of complex life. > > * Our orbit happens to lie in this fairly narrow band that allows for liquid water, and it seems other solvents don't...
Authors: Henri Lemoine, Thomas Lemoine, and Fraser Lee We are excited to introduce AlignmentSearch, an attempt to create a conversational agent that can answer questions about AI alignment. We built this site in response to ArthurB’s $5k bounty for a LessWrong conversational agent calling for the creation of a chatbot...
The following is a nitpick on an 18 year old blog post.
This fable is retold a lot. The progenitor of it as a rationalist mashal is probably Yudkowsky's classic sequence article. To adversarially summarize:
If the observer is distinct from Alice, absolutely. If the observer is Alice, nothing needs explaining in either case.
To put a bit of a crude metaphor on it, if you were to pick a random number uniformly between 0 and 1,000,000, and pre-commit to having a child on iff it's equal to some value X - from the point of view of the child, the probability that the number was equal to X is 100%.
Apologies if there's something more subtle with your answer that I've missed.
If the only observable outcome is the one in which we got that extremely lucky, then it doesn't need explaining. You only can observe outcomes compatible with the fact of you making an observation.
The standard argument usually goes something like this:
... (read 622 more words →)Alice: there's a lot about the Earth that seems suspiciously fine-tuned for the evolution of complex life.
- Our orbit happens to lie in this fairly narrow band that allows for liquid water, and it seems other solvents don't work nearly as well in supporting biochemistry.
- We've lucked into an ozone layer and a strong magnetic field, shielding us from cosmic rays and solar radiation.
- Our moon is far larger than we'd expect for a planet our size - to the extent that it might be more correct to classify the Earth-Moon system as a double planet. It's plausible that the lunar-powered periodic cycle of tidal conditions could have
Authors: Henri Lemoine, Thomas Lemoine, and Fraser Lee
We are excited to introduce AlignmentSearch, an attempt to create a conversational agent that can answer questions about AI alignment. We built this site in response to ArthurB’s $5k bounty for a LessWrong conversational agent calling for the creation of a chatbot capable of discussing bad AI Alignment takes, and guiding people new to the field through common misunderstandings and early points of confusion.
AlignmentSearch uses a dataset about AI alignment to construct a prompt for ChatGPT to answer AI alignment-related questions, while citing established sources. We qualitatively observe a massive boost in the quality of answers over ChatGPT without any specialized prompt, with results either on par or... (read 1122 more words →)