Posts

Sorted by New

Wikitag Contributions

Comments

Sorted by
yc1-1

Agreed on both points. I had to say, without reading the news occasionally, I do not realize how much I don’t know about things going on in the world. It does help me to stay informed, and deep concrete stories in particular, help to understand full pictures. Though many times, I also need to do a bit of digging to find more information to avoid bias, but if one stick to news sources that have better quality, this issue will be better. It is very likely the choice of news sources, matters. 

The OP had a strong assumption that whatever reported in the news are going to be mainstream; I think it is only partially true, and have some doubts; for “old” news, it is also/very possible they are getting attention bc nothing has been done about them. Things do not have to be new, to be underfunded/under resourced etc.

yc40

Terminology question - does adversarial filtering mean the same thing as decontamination? 

yc30

Could make this a report-based system? If the user reported a potential spam, then in the submission process ask for reasons, and ask for consent to look over the messages (between the reporter and the alleged spammer); if multiple people reported the same person it will be obvious this account is spamming with DM?

edit: just saw previous comment on this too

yc10

Thanks, I was thinking of the latter more (human irrationality), but found your first part still interesting. I understand irrationality was studied in psychology and economics, and I was wondering on the modeling of irrationality particularly, for 1-2 players, but also for a group of agents. For example, there are arguments saying for a group of irrational agents, the group choice could be rational depending on group structure etc. On individual irrationality and continued group irrationality, I think we would need to estimate the level of (and prevalence of ) irrationality in some way that captures unconscious preferences, or incomplete information. How to best combine these? Maybe it would just be just more data driven.

yc10

I am not sure if it needs to be conditional on if the event is unusual or not, or if would happen again or not in a forward looking sense in reality. Could you explain why the restriction there? Especially on <We do not call any behavior or emotional pattern ‘trauma’ if it is obviously adaptive.>

yc10

How do we best model an irrational world rationally? I would assume we would need to understand at least how irrationality works?

yc10

Sharing an interesting report of the state of ai https://www.stateof.ai/

This includes multiple aspects of the current state of AI, and is reasonably good on the technical side.

yc11

Just saw the OP replied in another comment that he is offering advice.

[This comment is no longer endorsed by its author]Reply
yc*30

It’s probably less on all internet but more on the rlhf guidelines (I imagine the human reviewers receive a guideline based on the LLM-training company’s policy, legal, and safety experts’ advice). I don’t disagree though that it could present a relatively more objective view on some topics than a particular individual (depending on the definition of bias).

yc10

Yeah for sure! 

For PII - A relatively recent survey paper: https://arxiv.org/pdf/2403.05156

For bias/fairness - survey paper: https://arxiv.org/pdf/2309.00770 

This is probably far from complete, but I think the references in the survey paper, and in the Staab et al. paper should have some additional good ones as well.

Load More