Major disruptions in businesses will start to appear around 2024 - i.e. profitable (by free cash flow) and hyper-growth companies relying on large-scale neural networks as their main tech strength.

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.

It's powered by LLMs. The value it brings is being testified widely.

The art market is relatively small but the stock image market might be much larger.

GitHub copilot is promising, but it's not human-level yet. It might be possible for Self-driving to use LLMs as foundations to build models that can predict the social behavior of humans on the street.

In SayCan, we showed how we can connect robot learning pipelines to large language models, bringing a lot of common sense knowledge to robotics. The hope was that as the LLMs become better (which they seem to be consistently doing), it will have a positive effect on robotics.

As widely believed, human has genetically encoded ability to learn and use syntax. This might greatly improve AI's linguistic faculties.

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. E.g. "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.

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.

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.

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/