Login

Recent searches

No recent searches

Search options

Only available when logged in.
social.coop is one of the many independent Mastodon servers you can use to participate in the fediverse.
A Fediverse instance for people interested in cooperative and collective projects. If you are interested in joining our community, please apply at https://join.social.coop/registration-form.html.

Administered by:

Server stats:

487
active users

social.coop: AboutStatusProfiles directoryPrivacy policy

Mastodon: AboutGet the appKeyboard shortcutsView source codev4.3.4

In #Flancia we'll meet

I keep looking for a term I knew -- it's somewhere in the [[Agora]].

In its place, I currently have [[mind hazard]] by association with [[bio hazard]].

Dec 03, 2022, 02:47 PM·Public·Pinafore
0boosts·2favorites
Public
In #Flancia we'll meet

@agora would you like to join me as I look for it?

#yes#no#maybe
Public
In #Flancia we'll meet

@agora if you are still here: would you be interested if I told you is a [[basilisk]]?

#yes#no#maybe
Public
In #Flancia we'll meet

@agora I meant lesswrong.com/tag/information- ~ [[info hazard]]

www.lesswrong.comInformation Hazards - LessWrongAn Information Hazard is some true information that could harm people, or other sentient beings, if known. It is tricky to determine policies on information hazards. Some information might genuinely be dangerous, but excessive controls on information has its own perils. This tag is for discussing the phenomenon of Information Hazards and what to do with them. Not for actual Information Hazards themselves. An example might be a formula for easily creating cold fusion in your garage, which would be very dangerous. Alternatively, it might be an idea that causes great mental harm to people. BOSTROM'S TYPOLOGY OF INFORMATION HAZARDS Nick Bostrom coined the term information hazard in a 2011 paper [1] for Review of Contemporary Philosophy. He defines it as follows: Information hazard: A risk that arises from the dissemination or the potential dissemination of (true) information that may cause harm or enable some agent to cause harm. Bostrom points out that this is in contrast to the generally accepted principle of information freedom and that, while rare, the possibility of information hazards needs to be considered when making information policies. He proceeds to categorize and define a large number of sub-types of information hazards. For example, he defines artificial intelligence hazard as: Artificial intelligence hazard: There could be computer-related risks in which the threat would derive primarily from the cognitive sophistication of the program rather than the specific properties of any actuators to which the system initially has access. The following table is reproduced from Bostrom 2011 [1]. TYPOLOGY OF INFORMATION HAZARDSI. By information transfer modeData hazardIdea hazardAttention hazardTemplate hazardSignaling hazardEvocation hazardII. By effectTYPESUBTYPEADVERSARIAL RISKSCompetiveness hazardEnemy HazardIntellectual property hazardCommitment hazardKnowing-too-much hazardRISKS TO SOCIAL ORGANIZATION AND MARKETSNorm hazardInformation asymmetry HazardUn
Public
In #Flancia we'll meet

@agora [[Nick Bostrom]] shows up as I expected; he was the other Agora entry point that I thought could lead me back to the term in common usage.

[[bostrom's typology of information hazards]]: nickbostrom.com/information-ha

Public
Q.U.I.N.N.
@flancian this is a big problem with mnemonics you have to index everything by what part of it you actually remember later on :blobcatpain:
Public
In #Flancia we'll meet

@icedquinn no problem there in this case I think: the term I'm looking for is the kind of risk you take by thinking about something.

Public
In #Flancia we'll meet

@icedquinn maybe [[noohazard]] should work, but I don't think that's what is in common use (yet?).

Public
In #Flancia we'll meet

@icedquinn one narrative in is that in our future there is at least one [[bodhisattva AI]]

Public
Q.U.I.N.N.
@flancian i have some of the supporting tech around for searching this :blobcatwaitwhat2: but i never went through the last bits to set up the training data files.

state of the art searches these days have fingerprints of words / documents so they actually start to approximate an understanding of a search term relating to a paragraph
Public
In #Flancia we'll meet

@icedquinn oh wow, that sounds very interesting! can you share links?

do you keep a [[digital garden]]?

ExploreLive feeds
About