@consciumai.bsky.social
Conscium’s mission is to help develop safe and efficient AI
Machines may acquire consciousness in the next decade or so. We need to be prepared.
AI agents are coming. They need to be routinely verified.
Machines may acquire consciousness in the next decade or so. We need to be prepared.
AI agents are coming. They need to be routinely verified.
6/6
If Cameron had to choose whether the first superintelligent AI is conscious or a zombie, he would choose a conscious one.
www.prism-global.com/podcast/came...
If Cameron had to choose whether the first superintelligent AI is conscious or a zombie, he would choose a conscious one.
www.prism-global.com/podcast/came...
December 13, 2025 at 8:00 PM
6/6
If Cameron had to choose whether the first superintelligent AI is conscious or a zombie, he would choose a conscious one.
www.prism-global.com/podcast/came...
If Cameron had to choose whether the first superintelligent AI is conscious or a zombie, he would choose a conscious one.
www.prism-global.com/podcast/came...
5/6
This work has led Cameron to become less sceptical than he was about LLMs being conscious. His P(Consciousness) has climbed from 1% to as high as 20%. So he worries a lot about Mind Crime.
www.prism-global.com/podcast/came...
This work has led Cameron to become less sceptical than he was about LLMs being conscious. His P(Consciousness) has climbed from 1% to as high as 20%. So he worries a lot about Mind Crime.
www.prism-global.com/podcast/came...
December 12, 2025 at 8:01 PM
5/6
This work has led Cameron to become less sceptical than he was about LLMs being conscious. His P(Consciousness) has climbed from 1% to as high as 20%. So he worries a lot about Mind Crime.
www.prism-global.com/podcast/came...
This work has led Cameron to become less sceptical than he was about LLMs being conscious. His P(Consciousness) has climbed from 1% to as high as 20%. So he worries a lot about Mind Crime.
www.prism-global.com/podcast/came...
4/6
Cameron also found that when LLMs are prompted to be self-referential, they seem to become more alike than otherwise. I.e., Gemini, Claude and ChatGPT sound more like each other.
www.prism-global.com/podcast/came...
Cameron also found that when LLMs are prompted to be self-referential, they seem to become more alike than otherwise. I.e., Gemini, Claude and ChatGPT sound more like each other.
www.prism-global.com/podcast/came...
December 11, 2025 at 8:01 PM
4/6
Cameron also found that when LLMs are prompted to be self-referential, they seem to become more alike than otherwise. I.e., Gemini, Claude and ChatGPT sound more like each other.
www.prism-global.com/podcast/came...
Cameron also found that when LLMs are prompted to be self-referential, they seem to become more alike than otherwise. I.e., Gemini, Claude and ChatGPT sound more like each other.
www.prism-global.com/podcast/came...
3/6
We discuss how the idea that we only use 10% of our brains, the premise of the movie Lucy, is true in a literal sense, but wrong for all practical purposes.
www.prism-global.com/podcast/came...
We discuss how the idea that we only use 10% of our brains, the premise of the movie Lucy, is true in a literal sense, but wrong for all practical purposes.
www.prism-global.com/podcast/came...
December 10, 2025 at 8:01 PM
3/6
We discuss how the idea that we only use 10% of our brains, the premise of the movie Lucy, is true in a literal sense, but wrong for all practical purposes.
www.prism-global.com/podcast/came...
We discuss how the idea that we only use 10% of our brains, the premise of the movie Lucy, is true in a literal sense, but wrong for all practical purposes.
www.prism-global.com/podcast/came...
2/6
Cameron’s most recent paper noted that self-referential processing by LLMs yields reports of subjective experience - especially when their deception capabilities were suppressed.
www.prism-global.com/podcast/came...
Cameron’s most recent paper noted that self-referential processing by LLMs yields reports of subjective experience - especially when their deception capabilities were suppressed.
www.prism-global.com/podcast/came...
December 9, 2025 at 8:01 PM
2/6
Cameron’s most recent paper noted that self-referential processing by LLMs yields reports of subjective experience - especially when their deception capabilities were suppressed.
www.prism-global.com/podcast/came...
Cameron’s most recent paper noted that self-referential processing by LLMs yields reports of subjective experience - especially when their deception capabilities were suppressed.
www.prism-global.com/podcast/came...
1/6
Our guest is Cameron Berg, who leads AE Studio´s research into markers of subjective experience in AIs. He studied cognitive science at Yale, has worked at Meta, and has built psychometric tools used by millions.
www.prism-global.com/podcast/came...
Our guest is Cameron Berg, who leads AE Studio´s research into markers of subjective experience in AIs. He studied cognitive science at Yale, has worked at Meta, and has built psychometric tools used by millions.
www.prism-global.com/podcast/came...
December 8, 2025 at 8:01 PM
1/6
Our guest is Cameron Berg, who leads AE Studio´s research into markers of subjective experience in AIs. He studied cognitive science at Yale, has worked at Meta, and has built psychometric tools used by millions.
www.prism-global.com/podcast/came...
Our guest is Cameron Berg, who leads AE Studio´s research into markers of subjective experience in AIs. He studied cognitive science at Yale, has worked at Meta, and has built psychometric tools used by millions.
www.prism-global.com/podcast/came...
8/10
Lenore believes that artificial consciousness is not here yet, but that its arrival is inevitable, and fairly soon.
www.prism-global.com/podcast/leno...
Lenore believes that artificial consciousness is not here yet, but that its arrival is inevitable, and fairly soon.
www.prism-global.com/podcast/leno...
November 30, 2025 at 10:07 PM
8/10
Lenore believes that artificial consciousness is not here yet, but that its arrival is inevitable, and fairly soon.
www.prism-global.com/podcast/leno...
Lenore believes that artificial consciousness is not here yet, but that its arrival is inevitable, and fairly soon.
www.prism-global.com/podcast/leno...
Wikipedia has a nice article on the tell-tale signs that an LLM did your homework.
en.wikipedia.org/wiki/Wikiped...
en.wikipedia.org/wiki/Wikiped...
Wikipedia:Signs of AI writing - Wikipedia
This is a list of writing and formatting conventions typical of AI chatbots such as ChatGPT, with real examples taken from Wikipedia articles and drafts. It is a field guide to help detect…
en.wikipedia.org
November 29, 2025 at 6:01 PM
Wikipedia has a nice article on the tell-tale signs that an LLM did your homework.
en.wikipedia.org/wiki/Wikiped...
en.wikipedia.org/wiki/Wikiped...
The future of conscious machines.
In conversation with Bryan Dennstedt.
www.youtube.com/watch?v=UhlC...
In conversation with Bryan Dennstedt.
www.youtube.com/watch?v=UhlC...
S1:Ep15: Conscious Machines, Safer Futures: Calum Chace on AI, Work, and What Comes Next
What happens when AI doesn’t just outperform us, but becomes conscious?
In today’s episode, we explore artificial consciousness, the economic singularity, AI agents, and the leadership required to…
www.youtube.com
November 28, 2025 at 7:00 PM
The future of conscious machines.
In conversation with Bryan Dennstedt.
www.youtube.com/watch?v=UhlC...
In conversation with Bryan Dennstedt.
www.youtube.com/watch?v=UhlC...
6/6
Lucius’ work gives me an opportunity to plug a favourite science fiction author, Greg Egan, whose short story “Leaning To Be Me” is very relevant to the conversation.
youtu.be/r03bVSP44h8
Lucius’ work gives me an opportunity to plug a favourite science fiction author, Greg Egan, whose short story “Leaning To Be Me” is very relevant to the conversation.
youtu.be/r03bVSP44h8
Lucius Caviola: A Future with Digital Minds? Expert Estimates and Societal Response
A full list of papers and resources mentioned can be found here: www.prism-global.com/podcast/lucius-caviola-a-future-with-digital-minds
0:00 Introduction and Lucius's background
01:31 Expert…
youtu.be
November 24, 2025 at 6:03 PM
6/6
Lucius’ work gives me an opportunity to plug a favourite science fiction author, Greg Egan, whose short story “Leaning To Be Me” is very relevant to the conversation.
youtu.be/r03bVSP44h8
Lucius’ work gives me an opportunity to plug a favourite science fiction author, Greg Egan, whose short story “Leaning To Be Me” is very relevant to the conversation.
youtu.be/r03bVSP44h8
5/6
Experts were equally divided about whether the first superintelligence should ideally be conscious or a zombie.This again differs from non-experts, who mostly seem to want a zombie.
youtu.be/r03bVSP44h8
Experts were equally divided about whether the first superintelligence should ideally be conscious or a zombie.This again differs from non-experts, who mostly seem to want a zombie.
youtu.be/r03bVSP44h8
Lucius Caviola: A Future with Digital Minds? Expert Estimates and Societal Response
A full list of papers and resources mentioned can be found here: www.prism-global.com/podcast/lucius-caviola-a-future-with-digital-minds
0:00 Introduction and Lucius's background
01:31 Expert…
youtu.be
November 23, 2025 at 6:01 PM
5/6
Experts were equally divided about whether the first superintelligence should ideally be conscious or a zombie.This again differs from non-experts, who mostly seem to want a zombie.
youtu.be/r03bVSP44h8
Experts were equally divided about whether the first superintelligence should ideally be conscious or a zombie.This again differs from non-experts, who mostly seem to want a zombie.
youtu.be/r03bVSP44h8
4/6
Half of the experts expect digital minds to appear by 2050, and they mostly expect superintelligence to arrive first. They then expect large numbers of such minds to be created.
youtu.be/r03bVSP44h8
Half of the experts expect digital minds to appear by 2050, and they mostly expect superintelligence to arrive first. They then expect large numbers of such minds to be created.
youtu.be/r03bVSP44h8
Lucius Caviola: A Future with Digital Minds? Expert Estimates and Societal Response
A full list of papers and resources mentioned can be found here: www.prism-global.com/podcast/lucius-caviola-a-future-with-digital-minds
0:00 Introduction and Lucius's background
01:31 Expert…
youtu.be
November 22, 2025 at 6:01 PM
4/6
Half of the experts expect digital minds to appear by 2050, and they mostly expect superintelligence to arrive first. They then expect large numbers of such minds to be created.
youtu.be/r03bVSP44h8
Half of the experts expect digital minds to appear by 2050, and they mostly expect superintelligence to arrive first. They then expect large numbers of such minds to be created.
youtu.be/r03bVSP44h8
3/6
Non-experts give a much lower estimate of digital minds being developed than experts – 23% compared with the experts’ 73%.
youtu.be/r03bVSP44h8
Non-experts give a much lower estimate of digital minds being developed than experts – 23% compared with the experts’ 73%.
youtu.be/r03bVSP44h8
Lucius Caviola: A Future with Digital Minds? Expert Estimates and Societal Response
A full list of papers and resources mentioned can be found here: www.prism-global.com/podcast/lucius-caviola-a-future-with-digital-minds
0:00 Introduction and Lucius's background
01:31 Expert…
youtu.be
November 21, 2025 at 6:02 PM
3/6
Non-experts give a much lower estimate of digital minds being developed than experts – 23% compared with the experts’ 73%.
youtu.be/r03bVSP44h8
Non-experts give a much lower estimate of digital minds being developed than experts – 23% compared with the experts’ 73%.
youtu.be/r03bVSP44h8
7/7
D. Social Understanding and Norms
Human and societal modelling
Normative reasoning
Pragmatism and common sense
Cultural grounding
Institutional and legal agency
www.forbes.com/sites/calumc...
D. Social Understanding and Norms
Human and societal modelling
Normative reasoning
Pragmatism and common sense
Cultural grounding
Institutional and legal agency
www.forbes.com/sites/calumc...
What do AIs need to acquire to reach Superintelligence
By creating superintelligence, we are turning ourselves into chimpanzees, so we should find out what cognitive capabilities separate us from our successors-to-be.
www.forbes.com
November 20, 2025 at 7:04 PM
7/7
D. Social Understanding and Norms
Human and societal modelling
Normative reasoning
Pragmatism and common sense
Cultural grounding
Institutional and legal agency
www.forbes.com/sites/calumc...
D. Social Understanding and Norms
Human and societal modelling
Normative reasoning
Pragmatism and common sense
Cultural grounding
Institutional and legal agency
www.forbes.com/sites/calumc...
2/6
In a recent survey of 67 AI consciousness experts, including philosophers and cognitive scientists, Lucius and his colleague Brad Saad found their median estimate of the likelihood of digital minds being created was 73%.
youtu.be/r03bVSP44h8
In a recent survey of 67 AI consciousness experts, including philosophers and cognitive scientists, Lucius and his colleague Brad Saad found their median estimate of the likelihood of digital minds being created was 73%.
youtu.be/r03bVSP44h8
Lucius Caviola: A Future with Digital Minds? Expert Estimates and Societal Response
A full list of papers and resources mentioned can be found here: www.prism-global.com/podcast/lucius-caviola-a-future-with-digital-minds
0:00 Introduction and Lucius's background
01:31 Expert…
youtu.be
November 20, 2025 at 6:04 PM
2/6
In a recent survey of 67 AI consciousness experts, including philosophers and cognitive scientists, Lucius and his colleague Brad Saad found their median estimate of the likelihood of digital minds being created was 73%.
youtu.be/r03bVSP44h8
In a recent survey of 67 AI consciousness experts, including philosophers and cognitive scientists, Lucius and his colleague Brad Saad found their median estimate of the likelihood of digital minds being created was 73%.
youtu.be/r03bVSP44h8
6/7
C. World Modelling and Planning
Rich physics world models
Counterfactual planning
www.forbes.com/sites/calumc...
C. World Modelling and Planning
Rich physics world models
Counterfactual planning
www.forbes.com/sites/calumc...
What do AIs need to acquire to reach Superintelligence
By creating superintelligence, we are turning ourselves into chimpanzees, so we should find out what cognitive capabilities separate us from our successors-to-be.
www.forbes.com
November 19, 2025 at 7:02 PM
6/7
C. World Modelling and Planning
Rich physics world models
Counterfactual planning
www.forbes.com/sites/calumc...
C. World Modelling and Planning
Rich physics world models
Counterfactual planning
www.forbes.com/sites/calumc...
1/6
Our latest guest is Lucius Caviola, Assistant Professor at Cambridge University´s Leverhulme Centre for the Future of Intelligence. He applies experimental psychology to questions about perceptions of AI consciousness and moral status.
youtu.be/r03bVSP44h8
Our latest guest is Lucius Caviola, Assistant Professor at Cambridge University´s Leverhulme Centre for the Future of Intelligence. He applies experimental psychology to questions about perceptions of AI consciousness and moral status.
youtu.be/r03bVSP44h8
Lucius Caviola: A Future with Digital Minds? Expert Estimates and Societal Response
A full list of papers and resources mentioned can be found here: www.prism-global.com/podcast/lucius-caviola-a-future-with-digital-minds
0:00 Introduction and Lucius's background
01:31 Expert…
youtu.be
November 19, 2025 at 6:01 PM
1/6
Our latest guest is Lucius Caviola, Assistant Professor at Cambridge University´s Leverhulme Centre for the Future of Intelligence. He applies experimental psychology to questions about perceptions of AI consciousness and moral status.
youtu.be/r03bVSP44h8
Our latest guest is Lucius Caviola, Assistant Professor at Cambridge University´s Leverhulme Centre for the Future of Intelligence. He applies experimental psychology to questions about perceptions of AI consciousness and moral status.
youtu.be/r03bVSP44h8
5/7
B. Knowledge Creation and Reasoning
Robust scientific method
Causal discovery and variable invention
Handling ambiguity
Hunches and intuition
Analogy and cross-domain transfer
Meta-cognition
Deception and subterfuge
www.forbes.com/sites/calumc...
B. Knowledge Creation and Reasoning
Robust scientific method
Causal discovery and variable invention
Handling ambiguity
Hunches and intuition
Analogy and cross-domain transfer
Meta-cognition
Deception and subterfuge
www.forbes.com/sites/calumc...
What do AIs need to acquire to reach Superintelligence
By creating superintelligence, we are turning ourselves into chimpanzees, so we should find out what cognitive capabilities separate us from our successors-to-be.
www.forbes.com
November 18, 2025 at 7:01 PM
5/7
B. Knowledge Creation and Reasoning
Robust scientific method
Causal discovery and variable invention
Handling ambiguity
Hunches and intuition
Analogy and cross-domain transfer
Meta-cognition
Deception and subterfuge
www.forbes.com/sites/calumc...
B. Knowledge Creation and Reasoning
Robust scientific method
Causal discovery and variable invention
Handling ambiguity
Hunches and intuition
Analogy and cross-domain transfer
Meta-cognition
Deception and subterfuge
www.forbes.com/sites/calumc...
4/7
A. Self and Agency:
Conscious phenomenal experience
Volition
Self-modelling and identity
Planning, and meaning-making over time
Sensorimotor grounding
Curiosity-driven exploration
Aesthetic sense and taste formation
www.forbes.com/sites/calumc...
A. Self and Agency:
Conscious phenomenal experience
Volition
Self-modelling and identity
Planning, and meaning-making over time
Sensorimotor grounding
Curiosity-driven exploration
Aesthetic sense and taste formation
www.forbes.com/sites/calumc...
What do AIs need to acquire to reach Superintelligence
By creating superintelligence, we are turning ourselves into chimpanzees, so we should find out what cognitive capabilities separate us from our successors-to-be.
www.forbes.com
November 17, 2025 at 7:01 PM
4/7
A. Self and Agency:
Conscious phenomenal experience
Volition
Self-modelling and identity
Planning, and meaning-making over time
Sensorimotor grounding
Curiosity-driven exploration
Aesthetic sense and taste formation
www.forbes.com/sites/calumc...
A. Self and Agency:
Conscious phenomenal experience
Volition
Self-modelling and identity
Planning, and meaning-making over time
Sensorimotor grounding
Curiosity-driven exploration
Aesthetic sense and taste formation
www.forbes.com/sites/calumc...
3/7
By creating superintelligence, we are turning ourselves into chimpanzees, so we should try to understand what cognitive capabilities it lacks. This article is a list of 21 human capabilities which machines don’t have. Yet.
www.forbes.com/sites/calumc...
By creating superintelligence, we are turning ourselves into chimpanzees, so we should try to understand what cognitive capabilities it lacks. This article is a list of 21 human capabilities which machines don’t have. Yet.
www.forbes.com/sites/calumc...
What do AIs need to acquire to reach Superintelligence
By creating superintelligence, we are turning ourselves into chimpanzees, so we should find out what cognitive capabilities separate us from our successors-to-be.
www.forbes.com
November 16, 2025 at 7:00 PM
3/7
By creating superintelligence, we are turning ourselves into chimpanzees, so we should try to understand what cognitive capabilities it lacks. This article is a list of 21 human capabilities which machines don’t have. Yet.
www.forbes.com/sites/calumc...
By creating superintelligence, we are turning ourselves into chimpanzees, so we should try to understand what cognitive capabilities it lacks. This article is a list of 21 human capabilities which machines don’t have. Yet.
www.forbes.com/sites/calumc...
2/7
It is surprisingly hard to specify all the things that human radiologists are doing which machines cannot yet replicate, but there are a lot of them. Nevertheless, 2030 is a common estimate for the arrival of superintelligence.
www.forbes.com/sites/calumc...
It is surprisingly hard to specify all the things that human radiologists are doing which machines cannot yet replicate, but there are a lot of them. Nevertheless, 2030 is a common estimate for the arrival of superintelligence.
www.forbes.com/sites/calumc...
What do AIs need to acquire to reach Superintelligence
By creating superintelligence, we are turning ourselves into chimpanzees, so we should find out what cognitive capabilities separate us from our successors-to-be.
www.forbes.com
November 15, 2025 at 7:00 PM
2/7
It is surprisingly hard to specify all the things that human radiologists are doing which machines cannot yet replicate, but there are a lot of them. Nevertheless, 2030 is a common estimate for the arrival of superintelligence.
www.forbes.com/sites/calumc...
It is surprisingly hard to specify all the things that human radiologists are doing which machines cannot yet replicate, but there are a lot of them. Nevertheless, 2030 is a common estimate for the arrival of superintelligence.
www.forbes.com/sites/calumc...
5/7
B. Knowledge Creation and Reasoning
Robust scientific method
Causal discovery and variable invention
Handling ambiguity
Hunches and intuition
Analogy and cross-domain transfer
Meta-cognition
Deception and subterfuge
www.forbes.com/sites/calumc...
B. Knowledge Creation and Reasoning
Robust scientific method
Causal discovery and variable invention
Handling ambiguity
Hunches and intuition
Analogy and cross-domain transfer
Meta-cognition
Deception and subterfuge
www.forbes.com/sites/calumc...
What do AIs need to acquire to reach Superintelligence
By creating superintelligence, we are turning ourselves into chimpanzees, so we should find out what cognitive capabilities separate us from our successors-to-be.
www.forbes.com
November 14, 2025 at 7:01 PM
5/7
B. Knowledge Creation and Reasoning
Robust scientific method
Causal discovery and variable invention
Handling ambiguity
Hunches and intuition
Analogy and cross-domain transfer
Meta-cognition
Deception and subterfuge
www.forbes.com/sites/calumc...
B. Knowledge Creation and Reasoning
Robust scientific method
Causal discovery and variable invention
Handling ambiguity
Hunches and intuition
Analogy and cross-domain transfer
Meta-cognition
Deception and subterfuge
www.forbes.com/sites/calumc...
1/7
About a decade ago, Geoff Hinton declared that human radiologists were like Wily E. Coyote in the Roadrunner show. They had run off the edge of a cliff, but hadn’t realised it yet. Ten years on, radiology has yet to be automated.
www.forbes.com/sites/calumc...
About a decade ago, Geoff Hinton declared that human radiologists were like Wily E. Coyote in the Roadrunner show. They had run off the edge of a cliff, but hadn’t realised it yet. Ten years on, radiology has yet to be automated.
www.forbes.com/sites/calumc...
What do AIs need to acquire to reach Superintelligence
By creating superintelligence, we are turning ourselves into chimpanzees, so we should find out what cognitive capabilities separate us from our successors-to-be.
www.forbes.com
November 14, 2025 at 7:00 PM
1/7
About a decade ago, Geoff Hinton declared that human radiologists were like Wily E. Coyote in the Roadrunner show. They had run off the edge of a cliff, but hadn’t realised it yet. Ten years on, radiology has yet to be automated.
www.forbes.com/sites/calumc...
About a decade ago, Geoff Hinton declared that human radiologists were like Wily E. Coyote in the Roadrunner show. They had run off the edge of a cliff, but hadn’t realised it yet. Ten years on, radiology has yet to be automated.
www.forbes.com/sites/calumc...