Seed AI

TagLast edit: 24 Sep 2021 22:01 UTC by plex

A Seed AI (a term coined by Eliezer Yudkowsky) is an Artificial General Intelligence (AGI) which improves itself by recursively rewriting its own source code without human intervention. Initially this program would likely have a minimal intelligence, but over the course of many iterations it would evolve to human-equivalent or even trans-human reasoning. The key for successful AI takeoff would lie in creating adequate starting conditions.


The notion of machine learning without human intervention has been around nearly as long as the computers themselves. In 1959, Arthur Samuel stated that “Machine learning is the field of study that gives computers the ability to learn without being explicitly programmed.”1 Since that time, computers have been able to learn by a variety of methods, including neural networks and Bayesian inference.

While these approaches have enabled machines to become better at various tasks2 3, it has not enabled them to overcome the limitations of these techniques, nor has it given them the ability to understand their own programming and make improvements. Hence, they are not able to adapt to new situations without human assistance.


A Seed AI has abilities that previous approaches lack:

This combination of abilities would, in theory, allow an AGI to recursively improve itself by becoming smarter within its original purpose. A Gödel machine rigorously defines a specification for such an AGI.


Currently, there are no known Seed AIs in existence, but it is an active field of research. Several organizations continue to pursue this goal, such as the Singularity Institute, OpenCog, and Adaptive AI.

See Also


  1. Han, Zhimeng. Smoothing in Probability Estimation Trees. The University of Waikato.

  2. Jump up↑ Lenat, Douglas. Eurisko. A program that learns news heuristics and domain concepts.. Artificial Intelligence.

  3. Jump up↑ Chellapilla, Kumar; Fogel, David. Evolving an Expert Checkers Playing Program without Using Human Expertise. Natural Selection, Inc.

  4. Yudkowsky, Eliezer.Seed AI Levels of Organization in General Intelligence. Singularity Institute.

  5. General Intelligence and Seed AI. Singularity Institute.

  6. Schmidhuber, Jürgen. Gödel Machines: Self-Referential Universal Problem Solvers Making Provably Optimal Self-Improvements. IDSIA

Wanted: backup plans for “seed AI turns out to be easy”

Wei Dai28 Sep 2011 21:54 UTC
29 points
64 comments2 min readLW link

[Question] Is “Re­cur­sive Self-Im­prove­ment” Rele­vant in the Deep Learn­ing Paradigm?

DragonGod6 Apr 2023 7:13 UTC
32 points
36 comments7 min readLW link

Levels of AI Self-Im­prove­ment

avturchin29 Apr 2018 11:45 UTC
11 points
1 comment39 min readLW link

ACI#4: Seed AI is the new Per­pet­ual Mo­tion Machine

Akira Pyinya8 Jul 2023 1:17 UTC
−7 points
0 comments6 min readLW link

[Question] Trans­former trained on it’s own con­tent?

Micromegas1 Apr 2023 15:08 UTC
1 point
0 comments1 min readLW link

[Question] Is a Self-Iter­at­ing AGI Vuln­er­a­ble to Thomp­son-style Tro­jans?

sxae25 Mar 2021 14:46 UTC
15 points
6 comments3 min readLW link