User Profile


Recent Posts

Curated Posts
starCurated - Recent, high quality posts selected by the LessWrong moderation team.
rss_feed Create an RSS Feed
Frontpage Posts
Posts meeting our frontpage guidelines: • interesting, insightful, useful • aim to explain, not to persuade • avoid meta discussion • relevant to people whether or not they are involved with the LessWrong community.
(includes curated content and frontpage posts)
rss_feed Create an RSS Feed
Personal Blogposts
personPersonal blogposts by LessWrong users (as well as curated and frontpage).
rss_feed Create an RSS Feed

Can corrigibility be learned safely?

3 min read
Show Highlightsubdirectory_arrow_left

Multiplicity of "enlightenment" states and contemplative practices

2 min read
Show Highlightsubdirectory_arrow_left

Combining Prediction Technologies to Help Moderate Discussions

Show Highlightsubdirectory_arrow_left

[link] Baidu cheats in an AI contest in order to gain a 0.24% advantage

Show Highlightsubdirectory_arrow_left

Is the potential astronomical waste in our universe too small to care about?

Show Highlightsubdirectory_arrow_left

What is the difference between rationality and intelligence?

Show Highlightsubdirectory_arrow_left

Six Plausible Meta-Ethical Alternatives

Show Highlightsubdirectory_arrow_left

Look for the Next Tech Gold Rush?

Show Highlightsubdirectory_arrow_left

Outside View(s) and MIRI's FAI Endgame

Show Highlightsubdirectory_arrow_left

Three Approaches to "Friendliness"

Show Highlightsubdirectory_arrow_left

Recent Comments

If you put 1/1000 the mass of a galaxy into radio signals over 10 GHz bandwidth over 10 billion years, you get [2.7e28 W/Hz]( power spectral density. According to [this paper](http://ads...(read more)

I suspect there may be a miscommunication here. To elaborate on "Relying purely on local validity won’t get you very far in playing chess", what I had in mind is that if you decided to play a move only if you can prove that's it's the optimal move, you won't get very far, since we can't produce proo...(read more)

> Don’t these numbers not add up? If mass is 1000x luminosity, and quasars are 100x galaxy, then how is the ratio 75x? The ratio for the sun is actually 1480 to be exact, plus the rest of the galaxy is apparently dimmer per unit mass than the sun is. For 1/1000x, I think if you put most of th...(read more)

I find your point 1 very interesting but point 2 may be based in part on a misunderstanding. > To expand on the last point, if A[*], the limiting agent, is aligned with H then it must contain at least implicitly some representation of H’s values (retrievable through IRL, for example). And so must...(read more)

One concern that I haven't seen anyone express yet is, if we can't discover a theory which assures us that IDA will stay aligned indefinitely as the amplifications iterate, it may become a risky yet extremely tempting piece of technology to deploy, possibly worsening the strategic situation from one...(read more)

> Main question is: do we see all the quasars at that distance, or do we see only a small fraction of them? Is whether we see them a simple function of power, in which case what is the cutoff?

I think yes, but it's a little hard to find a source that says this clearly. Basically modern surveys are ...(read more)


Though I guess you could just have several black holes, if one isn’t bright enough?

Exactly, you use as many as needed to reach the power you want.

> First, are there no naturally evaporating black holes? No, because small black holes evaporate too quickly and natural ones would have disappeared long ago, and large black holes evaporate too slowly to be used as an energy source (well technically you can use their accretion discs for matter-e...(read more)

Can the aliens convert matter completely into energy (for example by forming small black holes and letting them evaporate) or can they only use energy from fusion in stars? This makes about a [1000x difference]( more)

> [Note: I probably like explicit reasoning a lot more than most people, so keep that in mind.] Great! We need more people like you to help drive this forward. For example I think we desperately need explicit, worked out examples of meta-execution (see my request to Paul [here](https://www.lesswr...(read more)