Everything net
Everything relevant to the thought
... We do so by examining the cognitive abilities associated with three contemporary theories of conscious function: Global Workspace Theory (GWT), Information Generation Theory (IGT), and Attention Schema Theory (AST). ...
... We find that all three theories specifically relate conscious function to some aspect of domain-general intelligence in humans. ...
... With this insight, we turn to the field of Artificial Intelligence (AI) and find that, while still far from demonstrating general intelligence, many state-of-the-art deep learning methods have begun to incorporate key aspects of each of the three functional theories. ...
... 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. ...
... We believe that doing so can enable the development of artificial agents which are not only more generally intelligent but are also consistent with multiple current theories of conscious function. ...
1330 characters.
... [https://www.inc.com/bill-murphy-jr/how-emotionally-intelligent-people-use-send-a-bible-rule-to-become-remarkably-more-memorable.html](https://www.inc.com/bill-murphy-jr/how-emotionally-intelligent-people-use-send-a-bible-rule-to-become-remarkably-more-memorable.html) ...
470 characters.
... Where causality comes in is when we venture to model the 1/2 https://t.co/AmgYUOenjq ...
301 characters.
... Thread… Here’s my basic understanding of the model: the economy has some industries that are capital intensive and others that are not. When the central bank makes interest rates artificially low, it makes capital investment cheap and skews the economy toward capital intensive sectors. ...
... Society needs to produce fewer factories and machine tools and more beer and pairs of pants (or whatever). ...
... The period through the end of 2007 arguably fits the austrian model. There was arguably over investment in residential home construction. In 2006 and 2007 the home building industry was contracting while other industries were still growing. But in mid 2008, the situation changed. ...
... I can’t figure out how to explain this period with an Austrian model. I don’t see why anyone would consider this kind of mass unemployment necessary or how it set us up for stronger growth later. ...
2948 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.
... There's a widespread view in inflation hawk circles that the BLS came under political pressure (in the 1990s and maybe before) to modify the CPI to reduced the measured inflation rate and hence reduce how much the government would have to pay in Social Security benefits. ...
... The CPI, the one used for adjusting Social Security benefits, tends to come in higher than the PCE index. Right now, for example, PCE inflation is 5.7 percent while CPI inflation is 7 percent. ...
... So if Newt Gingrich forced the BLS to lower the CPI as a backdoor way of cutting Social Security payments, did he force the BEA to do the same thing so it wouldn't look suspicious? ...
1019 characters.
... This @JosephPolitano writeup is invaluable for understanding how this works. https://t.co/mmlaHCOVYW https://t.co/xtCyVhGzZl The use of OER to measure housing costs strikes a lot of people as goofy when they first hear about it. ...
... You could survey homeowners on their mortgage payments, but then would you price it based on the mortgages people actually pay (which would include people who bought homes 20 years ago and therefore have tiny payments) or what they would pay if they bought their house now? ...
933 characters.
... I'm reading @mattyglesias and thinking that bubble-phobia was a major factor behind the bad economic performance of the Bush and Obama years. https://t.co/p8zhQAIA2D https://t.co/xBi4kjjAXK In the early 2000s, people exaggerated the frothiness of the tech bubble and the harms from its crash. ...
... When a sluggish recovery finally started to gain steam in 2004-5, triggering a housing boom, people once again over-estimated its frothiness. This bubble frame caused the Fed to react too slowly to the onset of the Great Recession from December 2007 to September 2008. ...
... Then the idea that 1999 and 2006 were driven by unsustainable bubbles, as opposed to just being healthy economic booms, prevented people from recognizing how far the US economy was below potential from 2010 to 2015. ...
... People in the early 2010s assumed we had to live with a permanently shitty economy to avoid having more bubbles. But now we know that was wrong. The economy was still way below potential in 2015, and it's possible to recover rapidly from a recession with appropriate macro policy. ...
1418 characters.
... **Observation:** An observed empirical fact, indisputable for reasonable people. **Hypothesis:** A conjecture that is generalized from observations (induction), or deducted from other hypotheses (deduction). Collectively, hypotheses constitute our model (or theory) of the world. ...
... A hypothesis, often together with other hypotheses, can produce predictions. We use the broadest sense of this word, not limited to untested theories of how something works. It encompasses assumption, theory, putative knowledge, and the narrow sense of hypothesis. ...
... **Prediction:** A yet-to-be-made observation or (observational categorical per Quine). It's usually based on one or more hypotheses. The relationships between these categories of thoughts are fixed. In another sentence, there is an algebra in these elements of thoughts. ...
... This theory (or "hypothesis" as defined in itself) has [a philosophical basis](https://www.themind.net/hypotheses/M1qolEkbTje29ze62yEfQg): our knowledge of the world consists solely of prediction models. ...
... Out brain's intelligence is solely neurons trained to that predicts inputs working collectively. ...
1300 characters.
... 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.
... For example, she has shown that speakers of languages that use different words for different types of spatial relationships (e.g. "left" versus "right") are better at remembering the location of objects than speakers of languages that do not make this distinction. ...
264 characters.
... The brain learns by constantly making predictions and making corrections (in its wiring) to approach close to the actual results. ...
129 characters.
... The brain uses a mental language to represent and organize complex ideas and concepts. This mental language is thought to be distinct from natural languages like English or Spanish, and it is believed to be the medium through which we think and process information. ...
651 characters.
... All (actual and putative) knowledge has the same standards of success—the prediction of observation sentences. ...
110 characters.
... E.g. visual models of microscopic things. Physical symbols for abstract concepts. ...
81 characters.
... Here is an example: **Me**: I have a hypothesis. 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.