Open main menu
Home
Random
Recent changes
Special pages
Community portal
Preferences
About Wikipedia
Disclaimers
Incubator escapee wiki
Search
User menu
Talk
Dark mode
Contributions
Create account
Log in
Editing
Recursive self-improvement
(section)
Warning:
You are not logged in. Your IP address will be publicly visible if you make any edits. If you
log in
or
create an account
, your edits will be attributed to your username, along with other benefits.
Anti-spam check. Do
not
fill this in!
=== 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 [[Computer programming|program software]]. These capabilities include planning, reading, writing, [[compiling]], [[Software testing|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.<ref>{{Cite web |last=Readingraphics |date=2018-11-30 |title=Book Summary - Life 3.0 (Max Tegmark) |url=https://readingraphics.com/book-summary-life-3-0/ |access-date=2024-01-23 |website=Readingraphics |language=en-US}}</ref><ref>{{Cite book |last=Tegmark |first=Max |title=Life 3.0: Being a Human in the Age of Artificial Intelligence |date=August 24, 2017 |publisher=[[Vintage Books]], [[Allen Lane (imprint)|Allen Lane]]}}</ref><ref>{{Cite journal |last=Yudkowsky |first=Eliezer |title=Levels of Organization in General Intelligence |url=http://intelligence.org/files/LOGI.pdf |journal=Machine Intelligence Research Institute}}</ref> ==== Initial architecture ==== The initial architecture includes a goal-following [[Agent-based model|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:<ref name=":1">{{cite arXiv |last1=Zelikman |first1=Eric |title=Self-Taught Optimizer (STOP): Recursively Self-Improving Code Generation |date=2023-10-03 |eprint=2310.02304 |last2=Lorch |first2=Eliana |last3=Mackey |first3=Lester |last4=Kalai |first4=Adam Tauman|class=cs.CL }}</ref> * '''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-based model|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 orientation|Goal-oriented design]]''': The AGI is programmed with an initial goal, such as "improve your capabilities". This goal guides the system's actions and development trajectory. * '''Validation and Testing Protocols:''' An initial [[Test suite|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 [[Evolutionary algorithm|self-directed evolution]], where the agent can perform a kind of [[Selective breeding|artificial selection]], changing its software as well as its hardware. ==== General capabilities ==== This system forms a sort of generalist [[Turing completeness|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 to the internet, and integrate itself with external technologies. * Clone/[[Fork (software development)|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 [[Multimodal learning|multimodal architectures]] that further improve the capabilities of the [[Foundation model|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.
Edit summary
(Briefly describe your changes)
By publishing changes, you agree to the
Terms of Use
, and you irrevocably agree to release your contribution under the
CC BY-SA 4.0 License
and the
GFDL
. You agree that a hyperlink or URL is sufficient attribution under the Creative Commons license.
Cancel
Editing help
(opens in new window)