Everything net
Everything relevant to the thought... 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.
... pace seems to be slowing 1/ https://t.co/1a4025hPpu Couple this with expectations data: expected inflation up a lot for next year but not so much over next 5 years, suggesting consumers expect shock to be temporary 2/ https://t.co/JGj8kRXLhI https://t.co/PvRlPZ0vTp So far, then, no signs of a 70s-type ...
521 characters.
... 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-type ...
1419 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. ...
933 characters.
... This might be the single most important chart for understanding the current inflation situation. For 25 years prior to 2020, the prices of durable goods like cars, washing machines, and couches fell every single year. ...
1870 characters.
... I can also believe that money is more long-run neutral in high inflation environments. ...
2224 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. ...
2948 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.
... 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. ...
844 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. ...
... According to the LOTH, the structure and content of this mental language are shaped by the structure and content of the natural languages that we learn, but it is not identical to any one natural language. ...
... Instead, it is thought to be a universal language that is used by all humans to represent and process complex ideas. Link: https://plato.stanford.edu/entries/language-thought/ ...
651 characters.
... More precisely, LLMs model the concepts in natural languages using the language (albeit in a different syntax). Obviously, LLMs don't need to learn the concepts from scratch, they already have encoded words. ...
... More importantly, it doesn't need to learn a representation of the kinds of relationships between concepts, those are also encoded in words in the language as well, such as, "is", "belong to," "cause", etc. Here comes the more speculative part. ...
... To perform cognitive tasks, LLMs need to learn the specific relationships between specific concepts, and those relationships can be connections between a group of words, e.g., "swan", "black", "is", here "swan" and "black" are two concepts while "is" is the relationship between them. ...
... However, such groups of words can have multiple interpretations. Thus to truly encode a specific relationship, LLMs need to have connections embedded with syntax. e.g. it needs to encode the relationship between "black," and "swan" as "swan is black". i.e. ...
... A language phrase encodes the relationship. Thus one might be able to say that LLMs model the world in language. It might be a totally different gramma from natural language, but a syntax nonetheless and it's quite possible that this syntax is inspired by the syntax in natural language. ...
... The ability to model concepts using words, phrases and even sentences combined with syntax is critical. [It might be the reason we humans reached our level of intelligence](https://www.themind.net/hypotheses/8yof9E9YTYu4vHQI4qgBcw). ...
1529 characters.
... 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. ...
946 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.
... **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. ...
... 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. ...
... 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.