| Next revision | Previous revision |
| public:t-720-atai:atai-25:generality [2025/01/06 19:35] – created thorisson | public:t-720-atai:atai-25:generality [2025/01/06 19:37] (current) – [Requirements For AGI Systems] thorisson |
|---|
| |
| | {{public:t-720-atai:afteritleavesthelab.png?750|After it Leaves the Lab}} | | | {{public:t-720-atai:afteritleavesthelab.png?750|After it Leaves the Lab}} | |
| | **A:** Simple machine learners (**L<sub>0</sub>**) take a small set of inputs **(x, y, z)** and make a choice between a set of possible outputs **(α,β)**, as specified in detail by the system’s designer. Increasing either the set of inputs or number of possible outputs will either break the algorithm or slow learning to impractical levels. | | | **A:** Simple machine learners **(L<sub>0</sub>)** take a small set of inputs **(x, y, z)** and make a choice between a set of possible outputs **(α,β)**, as specified in detail by the system’s designer. Increasing either the set of inputs or number of possible outputs will either break the algorithm or slow learning to impractical levels. | |
| | **B:** Let **tsk<sub>i</sub>** refer to relatively non-trivial tasks such as assembling furniture and moving office items from one room to another, **S<sub>i</sub>** to various situations that a family of tasks can be performed, and <m>e_i</m> to environments where those situations may be encountered. Simple learner **L<sub>0</sub>** is limited to only a fraction of the various things that must be learned to achieve such a task. Being able to handle a single such task in a particular type of situation **(S<sub>1</sub>)** with features that were unknown prior to the system’s deployment, **L<sub>1</sub>** is already more capable than most if not all autonomous learning systems available today. **L<sub>2</sub>, L<sub>3</sub>** and **L<sub>4</sub>** take successive steps up the complexity ladder beyond that, being able to learn //numerous// complex tasks **(L<sub>2</sub>)**, in //various situations// **(L<sub>3</sub>)**, and in a wider range of //environments and mission spaces// **(L<sub>4</sub>)**. | | | **B:** Let **tsk<sub>i</sub>** refer to relatively non-trivial tasks such as assembling furniture and moving office items from one room to another, **S<sub>i</sub>** to various situations that a family of tasks can be performed, and <m>e_i</m> to environments where those situations may be encountered. Simple learner **L<sub>0</sub>** is limited to only a fraction of the various things that must be learned to achieve such a task. Being able to handle a single such task in a particular type of situation **(S<sub>1</sub>)** with features that were unknown prior to the system’s deployment, **L<sub>1</sub>** is already more capable than most if not all autonomous learning systems available today. **L<sub>2</sub>, L<sub>3</sub>** and **L<sub>4</sub>** take successive steps up the complexity ladder beyond that, being able to learn //numerous// complex tasks **(L<sub>2</sub>)**, in //various situations// **(L<sub>3</sub>)**, and in a wider range of //environments and mission spaces// **(L<sub>4</sub>)**. | |
| | Only towards the higher end of this ladder can we hope to approach really //general, autnomous// intelligence – systems capable of learning to effectively and efficiently perform multiple //a-priori unfamiliar// tasks, in //a variety of a-priori unfamiliar situations//, in a variety of //a-priori unfamiliar environments//, //**on their own**//. | | | Only towards the higher end of this ladder can we hope to approach really //general, autnomous// intelligence – systems capable of learning to effectively and efficiently perform multiple //a-priori unfamiliar// tasks, in //a variety of a-priori unfamiliar situations//, in a variety of //a-priori unfamiliar environments//, //**on their own**//. | |
| ====Requirements For AGI Systems==== | ====Requirements For AGI Systems==== |
| |
| ^Key^What it Means^Why it's Important^ | ^ Key ^What it Means^Why it's Important^ |
| | \\ Mission | **R1.** The system must fulfill its mission – the goals and constraints it has been given by its designers – with possibly several different priorities. | This is the very reason we built the system. We should have pretty good ideas as to why. Shared by all AI systems (in fact, all engineered systems). | | | \\ Mission | **R1.** The system must fulfill its mission – the goals and constraints it has been given by its designers – with possibly several different priorities. | This is the very reason we built the system. We should have pretty good ideas as to why. Shared by all AI systems (in fact, all engineered systems). | |
| | \\ AiLL \\ "After it Leaves the Lab" | **R2.** The system must be designed to be operational in the long-term, without intervention of its designers after it leaves the lab, as dictated by the temporal scope of its mission. | All machine learning methods today are "before it leaves the lab", meaning that the task-environment must be known and clearly delineated beforehand, and the system cannot handle changes to these assumptions. To be more autonomous we must look at the life of these systems "beyond the lab". | | | \\ AiLL \\ "After it Leaves the Lab" | **R2.** The system must be designed to be operational in the long-term, without intervention of its designers after it leaves the lab, as dictated by the temporal scope of its mission. | All machine learning methods today are "before it leaves the lab", meaning that the task-environment must be known and clearly delineated beforehand, and the system cannot handle changes to these assumptions. To be more autonomous we must look at the life of these systems "beyond the lab". | |
