-
Intermittent Distillations #1
| 3166 wordsThis is my low-budget version of Rohin’s Alignment Newsletter. A critique of pure learning and what artificial neural networks can learn from animal brains (Anthony M. Zador) A critique of pure learning and what artificial neural networks can learn from animal brains Summary This paper points out that human learning...
-
Strong Evidence is Common
| 289 wordsPortions of this are taken directly from Three Things I’ve Learned About Bayes’ Rule. One time, someone asked me what my name was. I said, “Mark Xu.” Afterward, they probably believed my name was “Mark Xu.” I’m guessing they would have happily accepted a bet at 20:1 odds that my...
-
Open Problems in Myopia
| 2405 wordsCoauthored with Evan Hubinger. Crossposted from the AI Alignment Forum. May contain more technical jargon than usual. Thanks to Noa Nabeshima for helpful discussion and comments. Introduction Certain types of myopic agents represent a possible way to construct safe AGI. We call agents with a time discount rate of zero...
-
Towards a Mechanistic Understanding of Goal-Directedness
| 1408 wordsCrossposted from the AI Alignment Forum. May contain more technical jargon than usual. This post is part of the research I have done at MIRI with mentorship and guidance from Evan Hubinger. Introduction Most discussion about goal-directed behavior has focused on a behavioral understanding, which can roughly be described as...
-
An Ode to My Parents
| 696 wordsSometimes I talk to my friends about their parents. I generally come away disoriented. I didn’t regard my parents as particularly exceptional; they were adequate at the task of raising me but not exemplary. However, what little I know about how parenting seems to work suggests that adequacy is exemplary....
-
Revenge of the Prediction Market
| 642 wordsRecommended reading: Prediction Markets: Tales from the Election Suppose I wanted to know the probability of some future event. How might I do this? One way would be to pay forecasters from the Good Judgment Project to forecast the event. These forecasters are generally pretty good at what they do,...
-
Maslow First and the World Second
| 652 wordsSaul McLeod: Maslow’s hierarchy of needs is a motivational theory in psychology comprising a five-tier model of human needs, often depicted as hierarchical levels within a pyramid. From the bottom of the hierarchy upwards, the needs are: physiological (food and clothing), safety (job security), love and belonging needs (friendship), esteem,...
-
How Simulacra Levels Increase
| 653 wordsSimulacra levels are an important and confusing concept. The concept itself is described reasonably well by the posts here. I’ve given my list of examples here. However, none of the descriptions I’ve read give a good explanation of why simulacra levels tend to rise. I now understand this process better...
-
Seriously, the Map is Not the Territory
| 243 wordsThe quotation is not the referent. “Snow is white “ is true if and only if snow is white. A model of reality is not reality. A prediction about what is going to happen is different from what actually happens. What you expect about reality is not reality. Your feelings...
-
Some People Are Smarter Than You
| 451 wordsAlice proposes a plan. Bob points out a flaw in the plan. However, Alice had already considered that flaw and thinks the plan is good despite the flaw (maybe the flaw doesn’t exist, maybe the second-best plan has an even worse flaw, etc.) If Bob thought for a few minutes,...