@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...
10/10
Lenore thinks Alan Turing would probably agree that his famous Test is better seen as a way to ascribe consciousness than to test for intelligence.
www.prism-global.com/podcast/leno...
Lenore thinks Alan Turing would probably agree that his famous Test is better seen as a way to ascribe consciousness than to test for intelligence.
www.prism-global.com/podcast/leno...
November 12, 2025 at 8:02 PM
10/10
Lenore thinks Alan Turing would probably agree that his famous Test is better seen as a way to ascribe consciousness than to test for intelligence.
www.prism-global.com/podcast/leno...
Lenore thinks Alan Turing would probably agree that his famous Test is better seen as a way to ascribe consciousness than to test for intelligence.
www.prism-global.com/podcast/leno...
9/10
Michael Graziano says that a non-conscious superintelligence would be a sociopath, whereas a conscious one could be empathetic. (Admittedly, humans can be sociopathic.) Given the choice, Lenore would opt for conscious superintelligence.
www.prism-global.com/podcast/leno...
Michael Graziano says that a non-conscious superintelligence would be a sociopath, whereas a conscious one could be empathetic. (Admittedly, humans can be sociopathic.) Given the choice, Lenore would opt for conscious superintelligence.
www.prism-global.com/podcast/leno...
November 11, 2025 at 10:09 PM
9/10
Michael Graziano says that a non-conscious superintelligence would be a sociopath, whereas a conscious one could be empathetic. (Admittedly, humans can be sociopathic.) Given the choice, Lenore would opt for conscious superintelligence.
www.prism-global.com/podcast/leno...
Michael Graziano says that a non-conscious superintelligence would be a sociopath, whereas a conscious one could be empathetic. (Admittedly, humans can be sociopathic.) Given the choice, Lenore would opt for conscious superintelligence.
www.prism-global.com/podcast/leno...
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 10, 2025 at 8:02 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...
7/10
The Blums´ CTM model has the advantage of being compatible with pretty much all the major theories of consciousness, like Global Workplace Theory, Integrated Information Theory, the four Es, and so on.
www.prism-global.com/podcast/leno...
The Blums´ CTM model has the advantage of being compatible with pretty much all the major theories of consciousness, like Global Workplace Theory, Integrated Information Theory, the four Es, and so on.
www.prism-global.com/podcast/leno...
November 9, 2025 at 8:01 PM
7/10
The Blums´ CTM model has the advantage of being compatible with pretty much all the major theories of consciousness, like Global Workplace Theory, Integrated Information Theory, the four Es, and so on.
www.prism-global.com/podcast/leno...
The Blums´ CTM model has the advantage of being compatible with pretty much all the major theories of consciousness, like Global Workplace Theory, Integrated Information Theory, the four Es, and so on.
www.prism-global.com/podcast/leno...
6/10
The Blums invented a multimodal language used by the brain called Brainish. The Brainish label for “rose” would consist of a certain smell, shape, colour, and texture.
www.prism-global.com/podcast/leno...
The Blums invented a multimodal language used by the brain called Brainish. The Brainish label for “rose” would consist of a certain smell, shape, colour, and texture.
www.prism-global.com/podcast/leno...
November 8, 2025 at 8:01 PM
6/10
The Blums invented a multimodal language used by the brain called Brainish. The Brainish label for “rose” would consist of a certain smell, shape, colour, and texture.
www.prism-global.com/podcast/leno...
The Blums invented a multimodal language used by the brain called Brainish. The Brainish label for “rose” would consist of a certain smell, shape, colour, and texture.
www.prism-global.com/podcast/leno...
5/10
Lenore explains the CTM model with an analogy of a partygoer who cannot remember the name of someone she met before. The brain contains multiple processors which shout replies, and a winner emerges by consensus. There is no central executive.
www.prism-global.com/podcast/leno...
Lenore explains the CTM model with an analogy of a partygoer who cannot remember the name of someone she met before. The brain contains multiple processors which shout replies, and a winner emerges by consensus. There is no central executive.
www.prism-global.com/podcast/leno...
November 7, 2025 at 8:02 PM
5/10
Lenore explains the CTM model with an analogy of a partygoer who cannot remember the name of someone she met before. The brain contains multiple processors which shout replies, and a winner emerges by consensus. There is no central executive.
www.prism-global.com/podcast/leno...
Lenore explains the CTM model with an analogy of a partygoer who cannot remember the name of someone she met before. The brain contains multiple processors which shout replies, and a winner emerges by consensus. There is no central executive.
www.prism-global.com/podcast/leno...
4/10
The Blum´s model of consciousness is the Conscious Turing Machine (CTM). It was inspired by Alan Turing’s model of computation, and Bernard Baars' Global Workspace Theory, although it is neither of those things itself.
www.prism-global.com/podcast/leno...
The Blum´s model of consciousness is the Conscious Turing Machine (CTM). It was inspired by Alan Turing’s model of computation, and Bernard Baars' Global Workspace Theory, although it is neither of those things itself.
www.prism-global.com/podcast/leno...
November 6, 2025 at 8:02 PM
4/10
The Blum´s model of consciousness is the Conscious Turing Machine (CTM). It was inspired by Alan Turing’s model of computation, and Bernard Baars' Global Workspace Theory, although it is neither of those things itself.
www.prism-global.com/podcast/leno...
The Blum´s model of consciousness is the Conscious Turing Machine (CTM). It was inspired by Alan Turing’s model of computation, and Bernard Baars' Global Workspace Theory, although it is neither of those things itself.
www.prism-global.com/podcast/leno...
3/10
Lenore and Manuel started to work together on a mathematical approach to consciousness during Covid. After 60+ years of marriage, she says they loved being thrown together by the pandemic.
www.prism-global.com/podcast/leno...
Lenore and Manuel started to work together on a mathematical approach to consciousness during Covid. After 60+ years of marriage, she says they loved being thrown together by the pandemic.
www.prism-global.com/podcast/leno...
November 5, 2025 at 8:01 PM
3/10
Lenore and Manuel started to work together on a mathematical approach to consciousness during Covid. After 60+ years of marriage, she says they loved being thrown together by the pandemic.
www.prism-global.com/podcast/leno...
Lenore and Manuel started to work together on a mathematical approach to consciousness during Covid. After 60+ years of marriage, she says they loved being thrown together by the pandemic.
www.prism-global.com/podcast/leno...
2/10
Lenore´s track record in computer science is so deep that she took the world´s first ever university course in it. It was given by the first winner of the Turing Prize, Alan Perlis.
www.prism-global.com/podcast/leno...
Lenore´s track record in computer science is so deep that she took the world´s first ever university course in it. It was given by the first winner of the Turing Prize, Alan Perlis.
www.prism-global.com/podcast/leno...
November 4, 2025 at 8:02 PM
2/10
Lenore´s track record in computer science is so deep that she took the world´s first ever university course in it. It was given by the first winner of the Turing Prize, Alan Perlis.
www.prism-global.com/podcast/leno...
Lenore´s track record in computer science is so deep that she took the world´s first ever university course in it. It was given by the first winner of the Turing Prize, Alan Perlis.
www.prism-global.com/podcast/leno...
1/10
Our latest guest is Lenore Blum, a storied mathematician with far more honours than will fit in one post, or even ten. She recently turned her attention to the problem of consciousness, which she works on with her partner Manuel and her son Avrim.
www.prism-global.com/podcast/leno...
Our latest guest is Lenore Blum, a storied mathematician with far more honours than will fit in one post, or even ten. She recently turned her attention to the problem of consciousness, which she works on with her partner Manuel and her son Avrim.
www.prism-global.com/podcast/leno...
November 3, 2025 at 8:00 PM
1/10
Our latest guest is Lenore Blum, a storied mathematician with far more honours than will fit in one post, or even ten. She recently turned her attention to the problem of consciousness, which she works on with her partner Manuel and her son Avrim.
www.prism-global.com/podcast/leno...
Our latest guest is Lenore Blum, a storied mathematician with far more honours than will fit in one post, or even ten. She recently turned her attention to the problem of consciousness, which she works on with her partner Manuel and her son Avrim.
www.prism-global.com/podcast/leno...
5/5
If Clara had to choose whether the first superintelligence is conscious or a zombie, she would choose a zombie. This is because she sees conscious entities as less predictable.
www.prism-global.com/podcast/clar...
If Clara had to choose whether the first superintelligence is conscious or a zombie, she would choose a zombie. This is because she sees conscious entities as less predictable.
www.prism-global.com/podcast/clar...
October 17, 2025 at 6:03 PM
5/5
If Clara had to choose whether the first superintelligence is conscious or a zombie, she would choose a zombie. This is because she sees conscious entities as less predictable.
www.prism-global.com/podcast/clar...
If Clara had to choose whether the first superintelligence is conscious or a zombie, she would choose a zombie. This is because she sees conscious entities as less predictable.
www.prism-global.com/podcast/clar...
4/5
Another of Clara’s studies suggests that when people attribute consciousness to AI, it reduces their trust in it, as opposed to intelligence, which builds trust.
www.prism-global.com/podcast/clar...
Another of Clara’s studies suggests that when people attribute consciousness to AI, it reduces their trust in it, as opposed to intelligence, which builds trust.
www.prism-global.com/podcast/clar...
October 16, 2025 at 6:03 PM
4/5
Another of Clara’s studies suggests that when people attribute consciousness to AI, it reduces their trust in it, as opposed to intelligence, which builds trust.
www.prism-global.com/podcast/clar...
Another of Clara’s studies suggests that when people attribute consciousness to AI, it reduces their trust in it, as opposed to intelligence, which builds trust.
www.prism-global.com/podcast/clar...
3/5
People who used LLMs more often were more prone to attributing consciousness to them.
www.prism-global.com/podcast/clar...
People who used LLMs more often were more prone to attributing consciousness to them.
www.prism-global.com/podcast/clar...
October 15, 2025 at 6:02 PM
3/5
People who used LLMs more often were more prone to attributing consciousness to them.
www.prism-global.com/podcast/clar...
People who used LLMs more often were more prone to attributing consciousness to them.
www.prism-global.com/podcast/clar...
2/5
Clara’s paper “Folk psychological attributions of consciousness to large language models” reports that in a 2023 survey of 300 US respondents, a remarkable 67% attributed consciousness to LLMs.
www.prism-global.com/podcast/clar...
Clara’s paper “Folk psychological attributions of consciousness to large language models” reports that in a 2023 survey of 300 US respondents, a remarkable 67% attributed consciousness to LLMs.
www.prism-global.com/podcast/clar...
October 14, 2025 at 6:02 PM
2/5
Clara’s paper “Folk psychological attributions of consciousness to large language models” reports that in a 2023 survey of 300 US respondents, a remarkable 67% attributed consciousness to LLMs.
www.prism-global.com/podcast/clar...
Clara’s paper “Folk psychological attributions of consciousness to large language models” reports that in a 2023 survey of 300 US respondents, a remarkable 67% attributed consciousness to LLMs.
www.prism-global.com/podcast/clar...
1/5
Clara Colombatto is an Assistant Professor of Psychology at the University of Waterloo in Canada, where her lab investigates the perception of other minds.
www.prism-global.com/podcast/clar...
Clara Colombatto is an Assistant Professor of Psychology at the University of Waterloo in Canada, where her lab investigates the perception of other minds.
www.prism-global.com/podcast/clar...
October 13, 2025 at 6:01 PM
1/5
Clara Colombatto is an Assistant Professor of Psychology at the University of Waterloo in Canada, where her lab investigates the perception of other minds.
www.prism-global.com/podcast/clar...
Clara Colombatto is an Assistant Professor of Psychology at the University of Waterloo in Canada, where her lab investigates the perception of other minds.
www.prism-global.com/podcast/clar...
6/6
Avalanche
Most people´s instinct is that structural unemployment will rise gradually, perhaps over several years. It is more likely to arrive suddenly. We need a plan. Now.
www.forbes.com/sites/calumc...
Avalanche
Most people´s instinct is that structural unemployment will rise gradually, perhaps over several years. It is more likely to arrive suddenly. We need a plan. Now.
www.forbes.com/sites/calumc...
October 3, 2025 at 7:03 PM
6/6
Avalanche
Most people´s instinct is that structural unemployment will rise gradually, perhaps over several years. It is more likely to arrive suddenly. We need a plan. Now.
www.forbes.com/sites/calumc...
Avalanche
Most people´s instinct is that structural unemployment will rise gradually, perhaps over several years. It is more likely to arrive suddenly. We need a plan. Now.
www.forbes.com/sites/calumc...
“One AI bubble has already burst – the bubble in saying there’s a bubble,”
The Deutsche Bank Research Institute says the number of web searches for “AI bubble” has plummeted in the past month.
The Deutsche Bank Research Institute says the number of web searches for “AI bubble” has plummeted in the past month.
October 2, 2025 at 8:00 PM
“One AI bubble has already burst – the bubble in saying there’s a bubble,”
The Deutsche Bank Research Institute says the number of web searches for “AI bubble” has plummeted in the past month.
The Deutsche Bank Research Institute says the number of web searches for “AI bubble” has plummeted in the past month.
5/6
Abundance
Of course, there is a catch. The real challenge is not meaning, but income. Without jobs, how will we all pay for the goods and services we need for a good life? Abundance is part of the answer, but distribution remains a hard problem.
www.forbes.com/sites/calumc...
Abundance
Of course, there is a catch. The real challenge is not meaning, but income. Without jobs, how will we all pay for the goods and services we need for a good life? Abundance is part of the answer, but distribution remains a hard problem.
www.forbes.com/sites/calumc...
October 2, 2025 at 7:03 PM
5/6
Abundance
Of course, there is a catch. The real challenge is not meaning, but income. Without jobs, how will we all pay for the goods and services we need for a good life? Abundance is part of the answer, but distribution remains a hard problem.
www.forbes.com/sites/calumc...
Abundance
Of course, there is a catch. The real challenge is not meaning, but income. Without jobs, how will we all pay for the goods and services we need for a good life? Abundance is part of the answer, but distribution remains a hard problem.
www.forbes.com/sites/calumc...