Macaulay

Wiki Contributions

Comments

AGI Safety FAQ / all-dumb-questions-allowed thread

But isn't it problematic to start the analysis at "superhuman AGI exists"? Then we need to make assumptions about how that AGI came into being. What are those assumptions, and how robust are they?

AGI Safety FAQ / all-dumb-questions-allowed thread

Why start the analysis at superhuman AGI? Why not solve the problem of aligning AI for the entire trajectory from current AI to superhuman AGI?

AGI safety from first principles: Conclusion

Also came here to say that 'latter' and 'former' are mixed up.

AGI safety from first principles: Control

In particular, we should be interested in how long it will take for AGIs to proceed from human-level intelligence to superintelligence, which we’ll call the takeoff period.

Why is this the right framing? Why not focus on the duration between 50% human-level and superintelligence? (Or p% human-level for general p.)

AGI safety from first principles: Superintelligence

So it seems very likely to me that eventually we will be able to create AIs that can generalise well enough to produce human-level performance on a wide range of tasks, including abstract low-data tasks like running a company.

Notice how unobjectionable this claim is: it's consistent with AGI being developed in a million years.

Voting is like donating thousands of dollars to charity

If you're loss averse, the expected value could easily be negative: cost(voting for wrong candidate) > benefit((voting for right candidate).

Intrinsic motivation is crucial for overcoming akrasia

I was astonished to find myself having ascended to the pantheon of those who have made major contributions to human knowledge

Is this your own evaluation of your work?

[FINAL CHAPTER] Harry Potter and the Methods of Rationality discussion thread, March 2015, chapter 122

If the "tear apart the stars" prophecy just refers to Harry harvesting the stars for resources, then Voldemort looks really stupid for misinterpreting it.

[FINAL CHAPTER] Harry Potter and the Methods of Rationality discussion thread, March 2015, chapter 122

Now Hermione learns Patronus 2.0 and destroys Azkaban. So both the Boy-Who-Lived and the Girl-Who-Revived can kill dementors. Sounds like "surviving/defeating Voldemort" is a plausible cover for explaining the origin of the ability to destroy dementors.

Harry Potter and the Methods of Rationality discussion thread, March 2015, chapter 120

Isn't Harry saying this to Draco after Draco has been obliviated? Draco has no idea what Harry's talking about.

Load More