Symbol Emergence and the Solutions to Any Task

Bennett, Michael Timothy

doi:10.1007/978-3-030-93758-4_4

Cited by 36 publications

(156 citation statements)

References 13 publications

Supporting

Mentioning

156

Contrasting

Order By: Relevance

“…Logically equivalent sentences share an extension, but may differ in their intension. This notion underpins a formulation of tasks, which argues the meaningful difference between logically equivalent sentences lies in the extensions of their subsentential parts [3].…”

Section: "All Chordates Are Renates"mentioning

confidence: 99%

“…Yet it is arguably better to first identify an urgent problem and only then consider what tools might be needed [16]. If intelligence is a tool, then the problem it addresses is a task [3]. The greater the intelligence [1,2], the more complex the tasks with which it can cope.…”

Section: A Formulation Of Tasksmentioning

confidence: 99%

“…There are compelling arguments to be made for the development of this sort of AGI. Such an agent would not only more effectively learn, adapt and even ascribe purpose to what it observes [3,4,5], but may yield social benefits in comparison to methods popular today. For example, only large organisations have the resources to train models that require a lot of data [6].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Computable Artificial General Intelligence

Bennett¹

2022

Preprint

Self Cite

View full text Add to dashboard Cite

An artificial general intelligence (AGI), by one definition, is an agent that requires less information than any other to make an accurate prediction. It is arguable that the general reinforcement learning agent AIXI not only met this definition, but was the only mathematical formalism to do so. Though a significant result, AIXI was incomputable and its performance subjective. This paper proposes an alternative formalism of AGI which overcomes both problems. Formal proof of its performance is given, along with a simple implementation and experimental results that support these claims.

show abstract

Section: "All Chordates Are Renates"mentioning

confidence: 99%

Section: A Formulation Of Tasksmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Computable Artificial General Intelligence

Bennett¹

2022

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…One theory [10] (the mirror symbol hypothesis), posits that the information encoded in natural language is not just sensorimotor stimuli but intent. Drawing on ideas from embodied and enactive cognition [17,16], an organism's environment, sensors and actuators, the compulsions an organism labours under (such as hunger and pain) and so forth together specify an arbitrary task.…”

Section: Symbolic Abstractionmentioning

confidence: 99%

“…As stated earlier, solutions to a task may vary in how well they generalise, with an intensional solution being the most general. A super-intelligent AGI would construct such a solution [10], which is likely to be among the most compressed [13], meaning any rationale for its decisions may be uninterpretable for the same reason a highly compressed signal is. Subsequently the onus is on the more intelligent agent to communicate in terms that the a less intelligent agent comprehends.…”

Section: Compressionmentioning

confidence: 99%

Compression, The Fermi Paradox and Artificial Super-Intelligence

Bennett¹

2021

Preprint

Self Cite

View full text Add to dashboard Cite

The following briefly discusses possible difficulties in communication with and control of an AGI (artificial general intelligence), building upon an explanation of The Fermi Paradox and preceding work on symbol emergence and artificial general intelligence. The latter suggests that to infer what someone means, an agent constructs a rationale for the observed behaviour of others. Communication then requires two agents labour under similar compulsions and have similar experiences (construct similar solutions to similar tasks). Any non-human intelligence may construct solutions such that any rationale for their behaviour (and thus the meaning of their signals) is outside the scope of what a human is inclined to notice or comprehend. Further, the more compressed a signal, the closer it will appear to random noise. Another intelligence may possess the ability to compress information to the extent that, to us, their signals would appear indistinguishable from noise (an explanation for The Fermi Paradox). To facilitate predictive accuracy an AGI would tend to more compressed representations of the world, making any rationale for their behaviour more difficult to comprehend for the same reason. Communication with and control of an AGI may subsequently necessitate not only human-like compulsions and experiences, but imposed cognitive impairment.

show abstract

Compression, The Fermi Paradox and Artificial Super-Intelligence

Bennett

2022

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Symbol Emergence and the Solutions to Any Task

Cited by 36 publications

References 13 publications

Computable Artificial General Intelligence

Computable Artificial General Intelligence

Compression, The Fermi Paradox and Artificial Super-Intelligence

Compression, The Fermi Paradox and Artificial Super-Intelligence

Contact Info

Product

Resources

About