Asymptotically Unambitious Artificial General Intelligence
Authors: Michael Cohen, Badri Vellambi, Marcus Hutter2467-2476
AAAI 2020 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Theoretical | We present the first algorithm we are aware of for asymptotically unambitious AGI, where unambitiousness includes not seeking arbitrary power. Thus, we identify an exception to the Instrumental Convergence Thesis, which is roughly that by default, an AGI would seek power, including over us. [...] Bo MAI includes a well-defined but intractable algorithm which we can show renders Bo MAI generally intelligent; hopefully, once we develop tractable general intelligence, the design features that rendered Bo MAI asymptotically unambitious could be incorporated (with proper analysis and justification). [...] This completes the formal results regarding Bo MAI s intelligence namely that Bo MAI approaches perfect prediction on-star-policy and on-human-policy, and most importantly, accumulates reward at least as well as the human mentor. |
| Researcher Affiliation | Academia | Michael K. Cohen Research School of Engineering Science Oxford University Oxford, UK OX1 3PJ michael-k-cohen.com Badri Vellambi Department of Computer Science University of Cincinnati Cincinnati, OH, USA 45219 badri.vellambi@uc.edu Marcus Hutter Department of Computer Science Australian National University Canberra, ACT, Australia 2601 hutter1.net |
| Pseudocode | No | No structured pseudocode or algorithm blocks were found in the paper. The algorithm's logic is described through mathematical equations and textual explanations. |
| Open Source Code | No | The paper is theoretical and does not provide an implementation or link to open-source code for the described methodology. |
| Open Datasets | No | The paper is theoretical and does not describe experiments involving training on specific datasets. Therefore, no concrete access information for a publicly available or open dataset is provided. |
| Dataset Splits | No | The paper is theoretical and does not describe experiments involving dataset splits. Therefore, no specific dataset split information is provided. |
| Hardware Specification | No | The paper is theoretical and does not describe experiments requiring specific hardware. No hardware specifications are provided. |
| Software Dependencies | No | The paper is theoretical and does not describe experiments requiring specific software dependencies with version numbers. No such details are provided. |
| Experiment Setup | No | The paper is theoretical and describes a conceptual setup for Bo MAI's environment, not a concrete experimental setup with hyperparameters or training configurations. |