Yes, one could express the conjunction ((A or B) and (C or D)) as the slightly longer, equivalent disjunction ((A and C) or (A and D) or (B and C) or (B and D)), but it’s worth pointing out that in addition to being longer, the disjunction is also highly structured… to wit, each individual atom appears twice in a systematic pattern. If atoms are chosen at random to fill in the slots, then you’re vanishingly unlikely to get a training goal that corresponds to a simple conjunction like the original. Of course, you could hand-code it to sometimes intentionally include examples that have the correct structure… but then, ah, you may as well code it to understand conjunctions directly, I think?
Axiomata
Karma: 32
- Axiomata 24 Aug 2021 16:15 UTC2 pointsin reply to: noggin-scratcher’s comment on: How DeepMind’s Generally Capable Agents Were Trained
“Only a crisis—actual or perceived—produces real change. When that crisis occurs, the actions that are taken depend on the ideas that are lying around. That, I believe, is our basic function: to develop alternatives to existing policies, to keep them alive and available until the politically impossible becomes politically inevitable.”—Milton Friedman, 1982 preface to Capitalism and Freedom