All of JohannWolfgang's Comments + Replies

One of the entrances to Theaterberg is closed, but you can take the other one or just sneak your way past the barricades.

I found the first part of the post a little bit cryptic (no pun intended). Since the second part is not just aimed at an audience with technical security knowledge, maybe at least including Shannon's maxim and a link to outfo-hazard (ok, that one is not technical) would help. Though after googling it, I still don't understand the part about Shannon's maxim, e.g.,

Generating a password with a high amount of "entropy" is just a way of ensuring that password crackers are very unlikely to break them without violating Shannon's maxim.

If Shannon's maxim is: "... (read more)

4lc2y
Violating shannon's maxim means making a security system that is insecure if an attacker knows how the system works. In this case, a password generation mechanism like "use the most memorable password not in the password cracking list" violates shannon's maxim - if an attacker knows you're doing that he can generate such passwords himself and test them against the password hash. A password generation mechanism like "select 18 random hexadecimal characters" is secure even if an attacker knows you're doing that, because you're randomly selecting from 16^18 possible passwords.

Considering that the default alternative would be no alignment research, I would say, yes, it is a net positive. But I also agree that alignment research can be dual use, which would be your second and third point. I don't think the first one is a big problem, since comparatively few AI researchers seems to care about the safety of AGI to start with. Even if you believe that some approaches to alignment will not help and can only provide a safe sense of certainty, pursuing them grows the field and can IMO only help attract more attention from the larger ML... (read more)

Thank you so much for your thoughtful comment! Specific pieces of advice like these are exactly what I am looking for. One question: what is the rationale behind the brightly colored items?

2cranberry_bear2y
I have heard this recommended by others but never looked into the research. Anecdotally I have found that very elderly patients/people with dementia react positively to colorful things. However, a casual googling of this revealed that "colorful stuff for dementia patients" is more of a "folk wisdom" being passed around as opposed to something with a rigorous backing (there are articles about the phenomenon like this: https://www.enablingenvironments.com.au/colour-perception-and-contrast.html). My theory of why it might be good is a) more sensory stimulation which keeps the brain active, especially in more severe cases b) helps them distinguish and remember the locations of different items more easily c) association with positive emotions (bright -> happy) d) as eyesight declines, brighter colors are required to elicit the same amount of attention / visual stimulation 

Agreeing with your post, I think it might be important to offer the people you want to reach out to a specific alternative what they should work on instead (because otherwise we are basically just telling them to quit their job, which nobody likes to hear). One such alternative would be AI alignment, but maybe that is not optimal for impatient people. I assume that researchers at OpenAI and DeepMind are in it because of the possibilities of advanced AI and that most of them are rather impatient to see them realized. Do you think it would be a good idea to ... (read more)

About the "senior doctors increase death rates" part, the imho most plausible explanation the authors of the study give is the following:

Second, declines in intensity of care during meetings—driven either by changes in physician composition and practice styles, reluctance to perform interventions in patients whose primary cardiologist is unavailable, or reluctance of cardiologists to intervene in high-risk patients without adequate back-up—may produce mortality reductions [...]

Which suggests that we should develop new criteria for when to operate or that p... (read more)

Concerning this passage about doctors:

You used that word “doctor” and my translator spit out a long sequence of words for Examiner plus Diagnostician plus Treatment Planner plus Surgeon plus Outcome Evaluator plus Student Trainer plus Business Manager. Maybe it’s stuck and spitting out the names of all the professions associated with medicine.

Does anybody know whether this idea is discussed anywhere else? Not being a medical expert myself I am sceptical that this idea is applicable to the full extent that seems to be implied here. It would only work if goo... (read more)