All of Betawolf's Comments + Replies

The author is associated with the Foundational Research Institute, which has a variety of interests highly connected to those of Lesswrong, yet some casual searches seem to show they've not been mentioned.

Briefly, they seem to be focused on averting suffering, with various outlooks on that including effective altruism outreach, animal suffering and ai-risk as a cause of great suffering.

Regarding the psychology of why people overestimate the correlation-causation link, I was just recently reading this, and something vaguely relevant struck my eye:

Later, Johnson-Laird put forward the theory that individuals reason by carrying out three fundamental steps [21]:

  1. They imagine a state of affairs in which the premises are true – i.e. they construct a mental model of them.

  2. They formulate, if possible, an informative conclusion true in the model.

  3. They check for an alternative model of the premises in which the putative conclusion is false.

... (read more)

I would be very surprised if this was not the case. Different fields already use different cutoffs for statistical-significance (you might get away with p<0.05 in psychology, but particle physics likes its five-sigmas, and in genomics the cutoff will be hundreds or thousands of times smaller and vary heavily based on what exactly you're analyzing) and likewise have different expectations for effect sizes (psychology expects large effects, medicine expects medium effects, and genomics expects very small effects; eg for genetic influence on IQ, any claim

... (read more)

It's hard to say because how would you measure this other than directly, and to measure this directly you need a clear set of correlations which are proposed to be causal, randomized experiments to establish what the true causal relationship is, and both categories need to be sharply delineated in advance to avoid issues of cherrypicking and retroactively confirming a correlation so you can say something like '11 out of the 100 proposed A->B causal relationships panned out'. This is pretty rare, although the few examples I've found from medicine tend t

... (read more)
4gwern
I would be very surprised if this was not the case. Different fields already use different cutoffs for statistical-significance (you might get away with p<0.05 in psychology, but particle physics likes its five-sigmas, and in genomics the cutoff will be hundreds or thousands of times smaller and vary heavily based on what exactly you're analyzing) and likewise have different expectations for effect sizes (psychology expects large effects, medicine expects medium effects, and genomics expects very small effects; eg for genetic influence on IQ, any claim of a allele with an effect larger than d=0.06 should be greeted with surprise and alarm). I think that there is going to be a relationship, but it'll be hard to describe precisely. Suppose we correlated A and B and found r=0.9. This is a large correlation by most fields' standards, and it would seem to put constraints on the causal net that A and B are part of: either there aren't many nodes 'in between' A and B (because each node is a chance for the correlation to diminish and be lost in influence from all the neighboring nodes, with their own connections) or the nodes are powerfully correlated so the net correlation can still be as high as 0.9. To a large extent, this is already the case (see above). People justify results with relation to implicit models and supposed analysis procedures ('we did reported t-test so we are entitled to declare p<0.05 statistically-significant (never mind all the tweaks we tried and interim tests while collecting data)'). The existing defaults aren't usually well-justified: for example, why does psychology use 0.05 rather than 0.10 or 0.01? 'Surely God loves p=0.06 almost as much as he loves the p=0.05' one line goes.

For the basic interaction setup, yes. For a sense of community and for reliable collection of the logs, perhaps not. I'm also not sure how anonymous Omegle makes users to each other and itself.

What I was getting at is that the current setup allows for side-channel methods of getting information on your opponent. (Digging to find their identity, reading their Facebook page, etc.).

While I accept that this interaction could be one of many between the AI and the researcher, this can be simulated in the anonymous case via a 'I was previously GatekeeperXXX, I'm looking to resume a game with AIYYY' declaration in the public channel while still preserving the player's anonymity.

0Shmi
By the way, wouldn't Omegle with the common interests specified as AIBOX basically do the trick?
Betawolf130

Prompted by Tuxedage learning to win, and various concerns about the current protocol, I have a plan to enable more AI-Box games whilst preserving the logs for public scrutiny.

See this: http://bæta.net/posts/anonymous-ai-box.html

3Gurkenglas
You forgot to adress Eliezers point that "10% of AI box experiments were won even by the human emulation of an AI" is more effective against future proponents of deliberately creating boxed AIs than "Careful, the guardian might be persuaded by these 15 arguments we have been able to think of". I don't think the probability of "AIs can find unboxing arguments we didn't" is sub-1 enough for preparation to matter. If there is any chance of a mathematical exhaustability of those arguments, its research should be conducted by a select circle of individuals that won't disclose our critical unboxers until a proof of safety.
9Tuxedage
I support this and I hope it becomes a thing.
4Shmi
That's not quite right. The AI and the researcher may have been interacting on the variety of issues before the AI decided to break out. This is nearly identical to Tuxedage talking to his future opponents on IRC or similar interactive media before they decided to run the experiment.