Integrated Information Theory
Article
Integrated Information Theory is a recurring concept in the Astral Codex Ten archive, appearing 3 times across 3 issues between May 13, 2022 and November 20, 2025. The archive places it in contexts such as “the Integrated Information Theory (IIT) by Giulio Tononi”; “the new open letter condemning the integrated information theory of consciousness”; “therefore integrated information theory should dub them conscious”. It most often appears alongside Anthropic, Europe, Giulio Tononi.
Metadata
- Category: Concepts
- Mention count: 3
- Issue count: 3
- First seen: May 13, 2022
- Last seen: November 20, 2025
Appears In
- Your Book Review: Consciousness And The Brain
- Links For September 2023
- The New AI Consciousness Paper
Related Pages
-
- Anthropic (2 shared issues)
-
- Europe (2 shared issues)
-
- Giulio Tononi (2 shared issues)
-
- OpenAI (2 shared issues)
-
- Scott Aaronson (2 shared issues)
-
- Tononi (2 shared issues)
-
- 2020 election (1 shared issues)
-
- @eigenrobot (1 shared issues)
-
- @jeremychrysler (1 shared issues)
-
- Adam Mastroianni (1 shared issues)
-
- Adversarial examples (1 shared issues)
-
- Aella (1 shared issues)
External Links
Source Context
Recovered passages from the original issue text. When the raw archive preserved outbound links inside the source passage, they are listed directly under the quote.
So should we say that the canton of Glarus becomes conscious once a year? Probably... not. There are similarities, and after reading this review you might understand what I mean if I call the Landsgemeinde a conscious event of Glarus. But in any other context, I would just cause utter confusion. More importantly, it goes against the intuitive meaning of consciousness for 99% of the people. So if we want to describe the concept of "all-parts-communicate-and-are-coherent-and-Granger-causal", then we should better invent a new name for it. Actually, there have been attempts to formalize and measure this, most famously the Integrated Information Theory (IIT) by Giulio Tononi. But the hope that this could give a formal definition of consciousness has the same problem as the idea that the Landsgemeinde is conscious. In a great rebuttal, Scott Aaronson has discussed the idea that IIT captures consciousness, and concluded that it "is wrong — demonstrably wrong, for reasons that go to its core. [This] puts it in something like the top 2% of all mathematical theories of consciousness ever proposed. Almost all competing theories of consciousness, it seems to me, have been so vague, fluffy, and malleable that they can only aspire to wrongness."
Inline links: In a great rebuttal
34: Neuroscientist Erik Hoel discusses the new open letter condemning the integrated information theory of consciousness. I agree with Hoel: IIT is a weird theory, and I don’t personally believe it, but the few attempts to test it have been mildly supportive (including the most recent). Consciousness is inherently hard to study, but IIT proponents (including Tononi, a true great of neuroscience) are trying their best and have behaved entirely responsibly. The signatories’ attempts to (without any argument) go straight to the media and tar it as “pseudoscience” and “misinformation” don’t lower my opinion of IIT at all, but does lower my opinion of the letter signatories. (EDIT: the signatories defend their perspective)
In 2004, neuroscientist Giulio Tononi proposed that consciousness depended on a certain computational property, the integrated information level, dubbed Φ. Computer scientist Scott Aaronson complained that thermostats could have very high levels of Φ, and therefore integrated information theory should dub them conscious. Tononi responded that yup, thermostats are conscious. It probably isn’t a very interesting consciousness. They have no language or metacognition, so they can’t think thoughts like “I am a thermostat”. They just sit there, dimly aware of the temperature. You can’t prove that they don’t.