Skip to content
AI Alignment Forum· Cole Wyeth·Indexed by this site · Originally published· Alignment →· Its place in the scan record →

Solomonoff induction based on reflective oracles

Solomonoff induction with reflective oracles

AI summary

A paper by PIBBSS researcher Damini Kusum proposes reflective oracle Solomonoff induction (rOSI), which can learn to extract computable structure from (partially) uncomputable sequences. Its sequence prediction properties are quite similar to logical induction, but the paper is much shorter and easier to read. The poster believes this is the clearest exposition of the idea in agent foundation research that "self-reflection can overcome unrealizability."

Related papers
Read originalalignmentforum.org