The second general point to be learned from the bitter lesson is that the actual contents of minds are tremendously, irredeemably complex; we should stop trying to find simple ways to think about the contents of minds, such as simple ways to think about space, objects, multiple agents, or symmetries. All these are part of the arbitrary, intrinsically-complex, outside world. They are not what should be built in, as their complexity is endless; instead we should build in only the meta-methods that can find and capture this arbitrary complexity.

The bitter lesson applies to alignment as well. Stop trying to think about "goal slots" whose circuit-level contents should be specified by the designers, or pining for a paradigm in which we program in a "utility function." That isn't how it works. See:

1. the failure of the agent foundations research agenda; 
2. the failed searches for "simple" safe wishes; 
3. the successful instillation of (hitherto-seemingly unattainable) corrigibility by instruction finetuning (no hardcoding!); 
4. the (apparent) failure of the evolved modularity hypothesis. 
   1. Don't forget that hypothesis's impact on classic AI risk! Notice how the following speculations about "explicit adaptations" violate information inaccessibility and also the bitter lesson of "online learning and search are. much more effective than hardcoded concepts and algorithms":
   2. From An Especially Elegant Evolutionary Psychology Experiment:
      1. "Humans usually do notice sunk costs—this is presumably either an adaptation to prevent us from switching strategies too often (compensating for an overeager opportunity-noticer?) or an unfortunate spandrel of pain felt on wasting resources." 
      2. "the parental grief adaptation"
      3. "this selection pressure was not only great enough to fine-tune parental grief, but, in fact, carve it out of existence from scratch in the first place."
   3. "The tendency to be corrupted by power is a specific biological adaptation, supported by specific cognitive circuits, built into us by our genes for a clear evolutionary reason. It wouldn’t spontaneously appear in the code of a Friendly AI any more than its transistors would start to bleed." (source)
   4. "In some cases, human beings have evolved in such fashion as to think that they are doing X for prosocial reason Y, but when human beings actually do X, other adaptations execute to promote self-benefiting consequence Z." (source)
   5. "When, today, you get into an argument about whether “we” ought to raise the minimum wage, you’re executing adaptations for an ancestral environment where being on the wrong side of the argument could get you killed."

Much of classical alignment theory violates now-known lessons about the nature of effective intelligence. These bitter lessons were taught to us by deep learning.

The bitter lesson is based on the historical observations that 1) AI researchers have often tried to build knowledge into their agents, 2) this always helps in the short term, and is personally satisfying to the researcher, but 3) in the long run it plateaus and even inhibits further progress, and 4) breakthrough progress eventually arrives by an opposing approach based on scaling computation by search and learning. 

The eventual success is tinged with bitterness, and often incompletely digested, because it is success over a favored, human-centric approach.