Everything net
Everything relevant to the thought... The authors here show that readiness to cooperate between individuals from different groups corresponds to the degree of cultural similarity between those groups. This is consistent with the theory of Cultural Group Selection as an explanation for the rise of human large-scale cooperation. ...
290 characters.
... In popular media, there is often a connection drawn between the advent of awareness in artificial agents and those same agents simultaneously achieving human or superhuman level intelligence. ...
... We find that all three theories specifically relate conscious function to some aspect of domain-general intelligence in humans. ...
... Given this apparent trend, we use the motivating example of mental time travel in humans to propose ways in which insights from each of the three theories may be combined into a unified model. ...
1330 characters.
... And now for something completely different. What the heck is going on with housing? Not just that prices are soaring, but they're soaring everywhere. ...
... I'm just curious about why this time is so different 4/ ...
548 characters.
... 4) The above rules are somewhat different for A.I. startups. There will be a FOMO race for top A.I. startups. I'm already seeing it. THAT said, if you are A.I. and profitable, you will demand double the valuation instantly. Nothing beats controlling your own destiny. ...
273 characters.
... In the Austrian theory, a recession is a process of resource re-allocation from capital-intensive to capital-light industries. Society needs to produce fewer factories and machine tools and more beer and pairs of pants (or whatever). ...
... In the Austrian theory, it’s important that central banks don’t interrupt this process by pushing interest rates back down to unnaturally low levels, because that interferes with this necessary re-allocation process. Ok so let’s think about 2006 to 2009. ...
2948 characters.
... This time the price rise is across the board, in fact in some cases higher in sprawl areas 2/ Eg Atlanta v Boston, on a log scale so you can see proportional differences: Boston >> Atlanta last time, if anything Atlanta > Boston now 3/ https://t.co/AbsuLsbbcY What's going on? ...
1012 characters.
... Yes, I know the HODLers see it as a buying opportunity, and they could be right — not doing price predictions, just trying to think this through 1/ First: crypto faithful comparing this to "crypto winter" of 2017-18, which was comparable in percentage terms. ...
1419 characters.
... It shows that COVID slowed the population growth rate in high-rent cities (San Francisco) much more than low-rent cities (like Grand Rapids) https://t.co/80TqyLh5y1 This chart illustrates how different the 2020 recovery was from 2007. ...
1929 characters.
... The controlled hallucination process is also a hypotheses-prediction-observation correction learning process. Brains can learn brand new concepts by generating new hypotheses about the world, making predictions about the sensory input, and correcting according to observation (actual sensory input) ...
298 characters.
... Suggested in [Being You](https://www.anilseth.com/being-you/), the perception process is a top-down "controlled hallucination." The brain predicts conceived "things" it will see and then "the sensory input" caused by them. ...
... Then the brain verifies or corrects the conceived things with the sensory input it actually receives. ...
324 characters.
... It enables the learning cycle of observations -> hypotheses -> predictions -> correct with observations. This can be argued for [philosophically](https://www.themind.net/hypotheses/W2wRBi5mSeGueEYevUjMzw) and [neuroscientifically](https://www.themind.net/hypotheses/M4p8C9lOTRu8ipf5zGtEJA). ...
422 characters.
... It's hard to imagine higher-level cognitive faculty without some form of hierarchical information processing. ATB proposed that such a hierarchy corresponds to the hierarchy of objects in the real world. This might be a bit too speculative. Columns learn from prediction errors. ...
... They can predict raw sensory inputs; they can also predict signals by other columns produced from sensory inputs. Thus, learning can happen when there are raw sensory input prediction errors as well as when there are other column signal prediction errors. ...
... Any column can learn from any other columns as long as their signals are useful. It's just that learning, and thus models, can happen orders away from raw input signals. ...
946 characters.
... High-level concepts and relationships between them exist linguistically in our brains, and cognitive functions based on these concepts and relationships are also encoded in sentences-like linguistic memories. Our brains can a) store models of the world in the sentences like linguistic memory. ...
... "Deers come to this spot when there is a drought." and b) Construct new knowledge/predictions by constructing new sentences following syntax rules E.g. "there is a drought now, if we go to this spot we might find deers." ...
... High-level human cognitive functions are the enterprise of our braining employing these two faculties. We don't have dedicated circuitries for each model expressed in linguistic memory, we just need the basic circuitries for language processing. ...
... Note that this hypothesis is different from linguistic determinism. ...
844 characters.
... Boroditsky has conducted a number of studies that have shown how the language we speak can influence our perception of time, space, and other aspects of our environment. For example, speakers of languages that use different words for different types of snow (e.g. ...
... "wet snow" versus "dry snow") are better at discriminating between different types of snow than speakers of languages that do not make this distinction. ...
416 characters.
... Tom's thinking process and decision-making barely come into his consciousness, but the actual process can be organized into observation, hypothesis, and prediction. When he entered the room, he made the observation that something looks like a chair in the room. ...
... Finally, he made the prediction that if he sits on it, he will be supported. ...
480 characters.
... Cortical columns make classifications based on raw sensory inputs as well as classification signals from other columns. They learn by predicting incoming raw sensory inputs as well as classification signals from other columns. ...
... One column's prediction error helps its own learning, as well as other columns' learning when the prediction was made with input from their classification signals. What do you think of my hypothesis? ...
... **ChatGPT**: Your hypothesis describes a process that is similar to how the brain is thought to process and classify sensory information. Cortical columns, which are groups of neurons in the cerebral cortex, are thought to play a role in processing and classifying sensory information. ...
... They do this by receiving input from sensory organs and then making predictions about what this input represents. These predictions are then compared to the actual input, and any discrepancies between the two are used to update the column's understanding of the sensory information. ...
... It is also thought that cortical columns communicate with each other, sharing information about the sensory input they have received and the predictions they have made. ...
... This can help to improve the overall accuracy of the predictions made by the brain, as different columns may have different strengths and areas of expertise in processing different types of sensory information. ...
... Overall, your hypothesis captures some of the key principles of how the brain processes and classifies sensory information, and it is generally consistent with current understanding of this process. ...
... However, it is important to note that the brain is a complex and multifaceted organ, and our understanding of how it works is still evolving. There may be additional factors and processes at play that are not captured in your hypothesis. ...
1869 characters.