Researcher bias and the hardware lottery contribute to apparent convergence in AI models beyond the proposed theoretical pressures

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

• Research gap: representational convergence in robotics has not been demonstrated at the same level as vision and languagequestion0.777
  Authors note robotics lacks a standardized representation approach and sufficient training data diversity to show PRH effects
• Constraints and biases of human intelligence are best avoided by ‘designing for emergence’ rather than implementing a pre-existing theory of intelligence.claim0.769
  Recommendation for creating non-anthropocentric machine intelligence.
• Conceptual advances in the links between machine learning and evolution now provide quantitative formalisms with which to begin to develop testable models of collective intelligence across scales.claim0.760
  Asserts that the time is ripe for formal models.
• Different models cannot converge to the same representation if they have access to fundamentally different information; convergence is capped by mutual information between input signalsclaim0.758
  Key limitation of the PRH for non-bijective observations
• Apparent success on binary detection tasks is entirely explained by mechanical logit shifts that bias models toward affirmative responses regardless of question contentclaim0.755
  Primary negative finding reinterpreted as methodological claim: binary paradigm is invalid for testing introspection
• We hypothesize that native self-report, fine-tuned introspection models, and trained activation-to-language systems will show different performance on bias-resistant localization and strength benchmarkshypothesis0.754
  Comparative prediction motivating future work contrasting different approaches to LLM self-knowledge
• Today's Large Language Models have become so good at playing Turing's game that it often takes experts to demonstrate the present limits of their ability to simulate human-like intelligence.claim0.749
  Paper's assessment of current LLM capabilities relative to Turing Test
• I don't follow AI alignment research in any depth, but I am noticing a striking disconnect between the concepts appearing in those discussions and recent advances in AI, especially GPT-3.quote0.749
  Quote from a question that sparked the post, highlighting the gap between theory and practice.