We Can't Understand AI Using our Existing Vocabulary

• URL: http://arxiv.org/abs/2502.07586v1
• Date: Tue, 11 Feb 2025 14:34:05 GMT
• Title: We Can't Understand AI Using our Existing Vocabulary
• Authors: John Hewitt, Robert Geirhos, Been Kim,
• Abstract summary: We argue that in order to understand AI, we cannot rely on our existing vocabulary of human words. We should strive to develop neologisms: new words that represent precise human concepts that we want to teach machines.
• Score: 22.352112061625768
• License:
• Abstract: This position paper argues that, in order to understand AI, we cannot rely on our existing vocabulary of human words. Instead, we should strive to develop neologisms: new words that represent precise human concepts that we want to teach machines, or machine concepts that we need to learn. We start from the premise that humans and machines have differing concepts. This means interpretability can be framed as a communication problem: humans must be able to reference and control machine concepts, and communicate human concepts to machines. Creating a shared human-machine language through developing neologisms, we believe, could solve this communication problem. Successful neologisms achieve a useful amount of abstraction: not too detailed, so they're reusable in many contexts, and not too high-level, so they convey precise information. As a proof of concept, we demonstrate how a "length neologism" enables controlling LLM response length, while a "diversity neologism" allows sampling more variable responses. Taken together, we argue that we cannot understand AI using our existing vocabulary, and expanding it through neologisms creates opportunities for both controlling and understanding machines better.

Related papers

• Machines of Meaning [0.0]
  We discuss the challenges in the specification of "machines of meaning" We highlight the need for detachment from anthropocentrism in the study of machines of meaning. We propose a view of "meaning" to facilitate the discourse around approaches such as neural language models.
  arXiv  Detail & Related papers  (2024-12-10T23:23:28Z)
• Explaining Explaining [0.882727051273924]
  Explanation is key to people having confidence in high-stakes AI systems. Machine-learning-based systems can't explain because they are usually black boxes. We describe a hybrid approach to developing cognitive agents.
  arXiv  Detail & Related papers  (2024-09-26T16:55:44Z)
• An Essay concerning machine understanding [0.0]
  This essay describes how we could go about constructing a machine capable of understanding. To understand a word is to know and be able to work with the underlying concepts for which it is an indicator.
  arXiv  Detail & Related papers  (2024-05-03T04:12:43Z)
• A Review on Objective-Driven Artificial Intelligence [0.0]
  Humans have an innate ability to understand context, nuances, and subtle cues in communication. Humans possess a vast repository of common-sense knowledge that helps us make logical inferences and predictions about the world. Machines lack this innate understanding and often struggle with making sense of situations that humans find trivial.
  arXiv  Detail & Related papers  (2023-08-20T02:07:42Z)
• Understanding Natural Language Understanding Systems. A Critical Analysis [91.81211519327161]
  The development of machines that guillemotlefttalk like usguillemotright, also known as Natural Language Understanding (NLU) systems, is the Holy Grail of Artificial Intelligence (AI) But never has the trust that we can build guillemotlefttalking machinesguillemotright been stronger than the one engendered by the last generation of NLU systems. Are we at the dawn of a new era, in which the Grail is finally closer to us?
  arXiv  Detail & Related papers  (2023-03-01T08:32:55Z)
• Do Artificial Intelligence Systems Understand? [0.0]
  It is not necessary to attribute understanding to a machine in order to explain its exhibited "intelligent" behavior. A merely syntactic and mechanistic approach to intelligence as a task-solving tool suffices to justify the range of operations that it can display.
  arXiv  Detail & Related papers  (2022-07-22T13:57:02Z)
• Emergence of Machine Language: Towards Symbolic Intelligence with Neural Networks [73.94290462239061]
  We propose to combine symbolism and connectionism principles by using neural networks to derive a discrete representation. By designing an interactive environment and task, we demonstrated that machines could generate a spontaneous, flexible, and semantic language.
  arXiv  Detail & Related papers  (2022-01-14T14:54:58Z)
• Inductive Biases for Deep Learning of Higher-Level Cognition [108.89281493851358]
  A fascinating hypothesis is that human and animal intelligence could be explained by a few principles. This work considers a larger list, focusing on those which concern mostly higher-level and sequential conscious processing. The objective of clarifying these particular principles is that they could potentially help us build AI systems benefiting from humans' abilities.
  arXiv  Detail & Related papers  (2020-11-30T18:29:25Z)
• Bongard-LOGO: A New Benchmark for Human-Level Concept Learning and Reasoning [78.13740873213223]
  Bongard problems (BPs) were introduced as an inspirational challenge for visual cognition in intelligent systems. We propose a new benchmark Bongard-LOGO for human-level concept learning and reasoning.
  arXiv  Detail & Related papers  (2020-10-02T03:19:46Z)
• Machine Common Sense [77.34726150561087]
  Machine common sense remains a broad, potentially unbounded problem in artificial intelligence (AI) This article deals with the aspects of modeling commonsense reasoning focusing on such domain as interpersonal interactions.
  arXiv  Detail & Related papers  (2020-06-15T13:59:47Z)
• Dark, Beyond Deep: A Paradigm Shift to Cognitive AI with Humanlike Common Sense [142.53911271465344]
  We argue that the next generation of AI must embrace "dark" humanlike common sense for solving novel tasks. We identify functionality, physics, intent, causality, and utility (FPICU) as the five core domains of cognitive AI with humanlike common sense.
  arXiv  Detail & Related papers  (2020-04-20T04:07:28Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.