Everything net
Everything relevant to the thought... 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. ...
... In this work, we explore the validity and potential application of this seemingly intuitive link between consciousness and intelligence. ...
... 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. ...
... 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.
... How to cultivate Asian heritage languages in the classroom for children from Asian immigrant families? For teachers who don't understand Asian heritage languages, how to encourage children's multilingual development in the classroom? ...
233 characters.
... When the central bank makes interest rates artificially low, it makes capital investment cheap and skews the economy toward capital intensive sectors. But that cheap credit hasn’t actually created any real resources, so you end up with increased spending on both capital and consumer goods. ...
... 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. ...
... 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. ...
2948 characters.
... Or believe that the Spanish economy suddenly lost all capacity for productivity gains in 2008? ...
... https://t.co/oaOKpGkvvd I wonder if what happened was that economists originally meant “money is more neutral in the long run than Keynesians thought in the 1960s” and over time that context has been forgotten. I can also believe that money is more long-run neutral in high inflation environments. ...
2224 characters.
... We've also made a small amount syndicating content to @Slate Prior to launching Full Stack Economics, I did some media consulting work for @shortwave, an email startup run by my brother, and earned $2,400. I offered to do this work for free but he said it was better to pay for legal reasons. ...
911 characters.
... If I'm reading the numbers right, around 800K bitcoins mined in 2021; at $50K each, that's around 0.2% of US GDP 5/ By contrast, residential investment peaked at almost 7% of GDP and fell by more than 4% 6/ https://t.co/PDSNM4BV7l And there surely isn't enough leveraged buying of crypto to create 2008 ...
1419 characters.
... Not all bad ideas come from the right 5/ ...
793 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. ...
... 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.
... 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. ...
... 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.
... That is, assign language tokens to objects. not just for communication, e.g., when young children name their dolls. Or when someone comes up with a new concept, they would eager to find a linguistic name for it, even before the need to communicate it. ...
251 characters.
... A system that lets users record their inquiry thoughts/ideas as observations, hypotheses, and predictions (OH&P) can provide a new mode of communication and collaboration between users - they can structurally connect their atomic OH&P directly to other users' OH&P. ...
... ([This is challenging](https://www.themind.net/observations/4fcVuFGoTEa43ez-xhSAsg) when thoughts/ideas are organized in the usual narrative structure, such as books, lectures, and talks). ...
... Such a system that connects atomic ideas and thoughts between users might achieve a **digitalized collective mind**. Digitalized mind means all ideas/thoughts are digitalized, collective meaning that these ideas/thoughts are contributed by multiple users and digitally connected to each other. ...
751 characters.
... **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. ...
... 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.
... Human has been organizing thoughts/ideas in story-like linear ways since the beginning of human culture. Books, talks, and lectures are all examples of such organizations. It's not the only way we convey ideas, e.g. day to day conversations usually are more or less structure-free and spontaneous. ...
... Ideas are bouncing in all directions. In the Internet age, Twitter and other social media provide new ways to perform such conversations multilaterally, but they are not well structured. ...
... The mainstream way to communicate larger groups of thoughts/ideas in a structured way remains to be the linear structure as in books, lectures, podcasts, etc. Though they have two main shortcomings 1. ...
921 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.
... 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. ...
946 characters.