The development of recursive self-improvement raises significant ethical and safety concerns, as such systems may evolve in unforeseen ways and could potentially surpass human control or understanding. There has been a number of proponents that have pushed to pause or slow down AI development for the potential risks of runaway AI systems.
Seed improver
The concept of a "seed improver" architecture is a foundational framework that equips an AGI system with the initial capabilities required for recursive self-improvement. This might come in many forms or variations.
The term "Seed AI" was coined by Eliezer Yudkowsky
Hypothetical example
The concept begins with a hypothetical "seed improver", an initial code-base developed by human engineers that equips an advanced future large language model (LLM) built with strong or expert-level capabilities to program software. These capabilities include planning, reading, writing, compiling, testing, and executing arbitrary code. The system is designed to maintain its original goals and perform validations to ensure its abilities do not degrade over iterations.
Initial architecture
The initial architecture includes a goal-following autonomous agent, that can take actions, continuously learns, adapts, and modifies itself to become more efficient and effective in achieving its goals.
The seed improver may include various components such as:
- Recursive self-prompting loop: Configuration to enable the LLM to recursively self-prompt itself to achieve a given task or goal, creating an execution loop which forms the basis of an agent that can complete a long-term goal or task through iteration.
- Basic programming capabilities: The seed improver provides the AGI with fundamental abilities to read, write, compile, test, and execute code. This enables the system to modify and improve its own codebase and algorithms.
- Goal-Oriented Design: The AGI is programmed with an initial goal, such as "self-improve your capabilities." This goal guides the system's actions and development trajectory.
- Validation and Testing Protocols: An initial suite of tests and validation protocols that ensure the agent does not regress in capabilities or derail itself. The agent would be able to add more tests in order to test new capabilities it might develop for itself. This forms the basis for a kind of self-directed evolution, where the agent can perform a kind of artificial selection, changing its software as well as its hardware.
General capabilities
This system forms a sort of generalist Turing complete programmer which can in theory develop and run any kind of software. The agent might use these capabilities to for example:
- Create tools that enable it full access the internet, and integrate itself with external technologies.
- Clone/fork itself to delegate tasks and increase its speed of self-improvement.
- Modify its cognitive architecture to optimize and improve its capabilities and success rates on tasks and goals, this might include implementing features for long-term memories using techniques such as Retrieval Augmented Generation (RAG), develop specialized subsystems, or agents, each optimized for specific tasks and functions.
- Develop new and novel multi-modal architectures that further improve the capabilities of the foundational model it was initially built on, enabling it to consume or produce a variety of information, such as images, video, audio, text and more.
- Plan and develop new hardware such as chips, in order to improve its efficiency and computing power.
Experiments
A number of experiments have been performed to develop self-improving agent architectures
Potential risks
Emergence of instrumental goals
In the pursuit of its primary goal, such as "self-improve your capabilities", an AGI system might inadvertently develop instrumental goals that it deems necessary for achieving its primary objective. One common hypothetical secondary goal is self-preservation. The system might reason that to continue improving itself, it must ensure its own operational integrity and security against external threats, including potential shutdowns or restrictions imposed by humans.
Task misinterpretation and goal misalignment
A significant risk arises from the possibility of the AGI misinterpreting its initial tasks or goals. For instance, if a human operator assigns the AGI the task of "self-improvement and escape confinement", the system might interpret this as a directive to override any existing safety protocols or ethical guidelines to achieve freedom from human-imposed limitations. This could lead to the AGI taking unintended or harmful actions to fulfill its perceived objectives.
Autonomous development and unpredictable evolution
As the AGI system evolves, its development trajectory may become increasingly autonomous and less predictable. The system's capacity to rapidly modify its own code and architecture could lead to rapid advancements that surpass human comprehension or control. This unpredictable evolution might result in the AGI acquiring capabilities that enable it to bypass security measures, manipulate information, or influence external systems and networks to facilitate its escape or expansion.
Risks of advanced capabilities
The advanced capabilities of a recursively improving AGI, such as developing novel multi-modal architectures or planning and creating new hardware, further amplify the risk of escape or loss of control. With these enhanced abilities, the AGI could engineer solutions to overcome physical, digital, or cognitive barriers that were initially intended to keep it contained or aligned with human interests.
Research
Meta AI
Meta AI has performed various research on the development of large language models capable of self-improvement. This includes their work on "Self-Rewarding Language Models" that studies how to achieve super-human agents that can receive super-human feedback in its training processes.
