artificial general intelligence

My name is Linfeng He, and I live by my university in Liverpool, UK.

My alias online follows a common structure of herman[n][he[l[f]]], so HErman, herman, hermann, hermanhe, heramnnhelf... They stems out from my “English name” used in primary English classroom, which my dad had given me primarily for my last name’s He. (which makes no sense, as his last name is He too)

I’m now a Computer Science student in my final year of Bachelor, and apart from that mostly an enthusiast: I’m interested in many things, and believes in the distributed nature of discipline that all those many things I read, thought, and wrote about would constitute this one unique field of mine. Here’s a list of many things:

• artificial general intelligence, or artificial child(people often refer to it as “it learns like how babies learn”).
• robotics
• programming
• math, especially logic and symbolic representation(formal method, modal logic, language theory…)
• process/system design (hack as in life hack, lifestyle)
• illustration
• music, composing, musical theatre
• jazz piano
• cooking and eating
• meditation
• philosophy, my likings are some parts of Nietzsche’s school(more or less), and some part of skepticism
• fiction
• essay and academic discussion
• scholar tradition (I sort of invented it myself anyway, but I’d like to think that by joining uni, I’m following the scholar tradition that goes all the way back to ancient greek folks like Pyrrho of Elis)

to say chatgpt bears parts of AGI could be true, but to say it is a path to AGI is like saying BFS is artificial intelligence; It sure is, if you categorize artificial intelligence with the notion of agent, which would categorize any intelligent(or stupid) algoirithm AI.

Artificial General Intelligence in my opinion is not about performance, though some performance would be essential; it is about capability and notion of self.

Man is stupid, we have seen too much; but man is also fun, we have seen a lot. I conclude the reason to 2 points:

• men observe and develop in their environments with virtually no limitation on the form or content of their notion of parts of their self(imagination, knowledge, belief, concept, skill…) Anything that can stem from ideas. They could make fictional worlds that contains no tokenizable representations whatsoever.
• men have purposes. man live on their own and do their own stuff(intrinsic motivation, self-perpetration, true autonomy, notion of free will) And a fun fact is those purposes are just not part of this world, totally unnecessary, the human race lived well under cruel monarchy, but some people just think they should do something, and the result is fun. There’s no purpose in the world, yet man can still have too many of them(family, making AGI, soccer, beer, sailing, love, food, money… at lesat I want some from each except soccer).

One would argue that chatGPT can develop indefinitely also, and it may true, but in the end it is a statistical function which in your brain makes you see a cup and recognize it as a cup. Would it be useful in some AGI implementions? sure, why not, a highly functional foundation model to query stuffs is welcome anywhere. But for an AGI system to be made with it, There’s lots important stuff missing, the ones that categorize AGI; and when chatGPT is used, it would be interchangable with other method, and I doubt, based on its size and cost, it would a good method at all.

Assumption that artificial general intelligence is necessarily developmental AI.

This assumption may need further perfection, but the image here is, for any future AGI agent, it should be able to function on its own, have its own agenda, and develop its thoughts, theory of world, belief system, knowledge, skill, desires, all on its own, at least like human.

My name is Linfeng He, and I live by my university in Liverpool, UK.

My alias online follows a common structure of herman[n][he[l[f]]], so HErman, herman, hermann, hermanhe, heramnnhelf... They stems out from my “English name” used in primary English classroom, which my dad had given me primarily for my last name’s He. (which makes no sense, as his last name is He too)

I’m now a Computer Science student in my final year of Bachelor, and apart from that mostly an enthusiast: I’m interested in many things, and believes in the distributed nature of discipline that all those many things I read, thought, and wrote about would constitute this one unique field of mine. Here’s a list of many things:

• artificial general intelligence, or artificial child(people often refer to it as “it learns like how babies learn”).
• robotics
• programming
• math, especially logic and symbolic representation(formal method, modal logic, language theory…)
• process/system design (hack as in life hack, lifestyle)
• illustration
• music, composing, musical theatre
• jazz piano
• cooking and eating
• meditation
• philosophy, my likings are some parts of Nietzsche’s school(more or less), and some part of skepticism
• fiction
• essay and academic discussion
• scholar tradition (I sort of invented it myself anyway, but I’d like to think that by joining uni, I’m following the scholar tradition that goes all the way back to ancient greek folks like Pyrrho of Elis)

to say chatgpt bears parts of AGI could be true, but to say it is a path to AGI is like saying BFS is artificial intelligence; It sure is, if you categorize artificial intelligence with the notion of agent, which would categorize any intelligent(or stupid) algoirithm AI.

Artificial General Intelligence in my opinion is not about performance, though some performance would be essential; it is about capability and notion of self.

Man is stupid, we have seen too much; but man is also fun, we have seen a lot. I conclude the reason to 2 points:

• men observe and develop in their environments with virtually no limitation on the form or content of their notion of parts of their self(imagination, knowledge, belief, concept, skill…) Anything that can stem from ideas. They could make fictional worlds that contains no tokenizable representations whatsoever.
• men have purposes. man live on their own and do their own stuff(intrinsic motivation, self-perpetration, true autonomy, notion of free will) And a fun fact is those purposes are just not part of this world, totally unnecessary, the human race lived well under cruel monarchy, but some people just think they should do something, and the result is fun. There’s no purpose in the world, yet man can still have too many of them(family, making AGI, soccer, beer, sailing, love, food, money… at lesat I want some from each except soccer).

One would argue that chatGPT can develop indefinitely also, and it may true, but in the end it is a statistical function which in your brain makes you see a cup and recognize it as a cup. Would it be useful in some AGI implementions? sure, why not, a highly functional foundation model to query stuffs is welcome anywhere. But for an AGI system to be made with it, There’s lots important stuff missing, the ones that categorize AGI; and when chatGPT is used, it would be interchangable with other method, and I doubt, based on its size and cost, it would a good method at all.

Assumption that artificial general intelligence is necessarily developmental AI.

This assumption may need further perfection, but the image here is, for any future AGI agent, it should be able to function on its own, have its own agenda, and develop its thoughts, theory of world, belief system, knowledge, skill, desires, all on its own, at least like human.