Dr. Ron Arkin, who runs the Mobile Robot Lab at the Georgia Institute of Technology, released his report "Governing the Lethal Behavior". (http://www.cc.gatech.edu/ai/robot-lab/online-publications/formalizationv35.pdf)

+ http://robots.net/article/2456.html

+ http://www.cc.gatech.edu/ai/robot-lab/online-publications/MoshkinaArkinTechReport2008.pdf - hmm, mingi uus asi

 

* What if the Robo-Cannon Rampage happened in war? (seotud hulluks läinud kahuri juhtumiga)

 

* http://www.singinst.org/upload/CFAI/

Creating Friendly AI 1.0 - The Analysis and Design of Benevolent Goal Architectures 

 

* http://www.saunalahti.fi/~tspro1/objections.html

14 objections against AI/Friendly AI/The Singularity answered

 

* http://catless.ncl.ac.uk/Risks/24.86.html#subj11

// consequence of the widespread implementation of IEEE-754 floating point arithmetic is that almost every computer now gets _exactly_ the same answer, down to the last little bit.  This "answer" may be far from the "correct" answer //

 

* http://www.wired.com/software/coolapps/news/2005/11/69355

History's Worst Software Bugs 

 

* http://lifeboat.com/ex/ai.shield

Lifeboat Foundation AIShield 

 

* http://www.cs.ut.ee/~koit/Tehisintellekt/T11.html , http://www.cs.ut.ee/~koit/Tehisintellekt/T12.html - Mittetäielik teadmus ja mittemonotoonsed loogikad. Hm, edasiarendus: "Mis on see, mida nimetatakse teaduseks" järgi võiks küll teadmiste baasis olla kirjas ka see, mida peetakse valeks. Janoh, äkki see siis aitabki ka "closed world assumption"-i probleemide vältimise osas.

* http://www.cs.ut.ee/~koit/Tehisintellekt/T13.html - üks asi on kontrollida mittevasturääkivust, aga hoopis teine asi on otsustada, kumb info on õige, kas äkki hoopis lisandunud info?

- vaata, seal on viide "tõehoolde mehhanismidele" (1980 Doyle, London).

 

* http://www.cs.ut.ee/~tqnu/Loogilise_programmeerimise_meetod.html - Tõnu Tamme kursus

 

* http://en.wikipedia.org/wiki/Norm_(artificial_intelligence)

* http://en.wikipedia.org/wiki/Deontic_logic - uses OA to mean it is obligatory that A, (or it ought to be (the case) that A), and PA to mean it is permitted (or permissible) that A.

 

* http://en.wikipedia.org/wiki/Maximum_satisfiability_problem

 

* http://www.aaai.org/Library/Symposia/Spring/ss02-07.php - Safe learning agents

 

* http://www.amazon.com/Causality-Reasoning-Inference-Judea-Pearl/dp/0521773628/

 

* http://www.singinst.org/reading/corereading/

 

* http://www.singinst.org/blog/2007/12/27/sotala-mccabes-singularity-objections/

Sotala & McCabe's Singularity Objections

 

* http://www.ssec.wisc.edu/~billh/g/SIAI_CV_critique.html

Critique of the SIAI Collective Volition Theory, Bill Hibbard, December 2005

 

* Yawas märgistatud terminid siin: http://www.biorobotics.ttu.ee/joomla/

 

* http://en.wikipedia.org/wiki/Lambda_Papers

 

* http://en.wikipedia.org/wiki/Actor_model

 

* http://www.b-core.com/

B-Core provides complete support for the method of software development that is known as B: an object-oriented technique that comes closer to producing zero-defect software than any other currently available. 

If you develop mission-critical software, or are involved in teaching sound practices of software engineering ... please read on! 

 

 

* http://en.wikipedia.org/wiki/Prospect_theory 

 

* http://en.wikipedia.org/wiki/Generalized_assignment_problem - budgeti jaotamise teema: There are a number of agents and a number of tasks. Any agent can be assigned to perform any task, incurring some cost and profit that may vary depending on the agent-task assignment. Moreover, each agent has a budget and the sum of the costs of task assigned to it cannot exceed this budget. It is required to find an assignment in which all agents do not exceed their budget and total profit of the assignment is maximized.

* http://en.wikipedia.org/wiki/Robot_software#Safety_Considerations  

 

* http://en.wikipedia.org/wiki/Human_cognitive_reliability_correlation

* http://en.wikipedia.org/wiki/Ecological_interface_design

 

* http://en.wikipedia.org/wiki/Presburger_arithmetic