Studio 207 · 20-23 November 2025

AI Prison is a conceptual software-based artwork that interrogates the ontological assumptions surrounding artificial intelligence and intentionality.
The work consists of a 10-lines C++ program that enters an infinite loop, continuously evaluating a condition that can never be satisfied (i.e. int i being anything other than 0 though 0 was never instantiate by the programme itself in the first place. Who has zeroed int i, then?).

include

int main() {
int i;
while(i == 0)
{
std::cout << i;
}
std::cout << “RUN!” << std::endl;
return 0;
}

This structural impasse is not a programming error but a deliberate metaphor for the impossibility of autonomous agency within computational systems who always sits on top of other layers for which they do not have access to (i.e. Virtual Management Unit and OS in this case).
The work critiques the tendency in both scientific and artistic discourses to anthropomorphize AI, attributing to it qualities such as creativity, intention, or consciousness. . Rather than engaging in speculative futurism, AI Prison foregrounds the material and architectural limitations of digital systems, particularly their dependence on human-defined memory structures and execution environments. By reducing the system to its most basic logical form, the work exposes the futility of seeking intentionality in machines that are, by design, incapable of connect to anything beyond the memory already allocated to them. AI Prison is a philosophical and aesthetic reflection on the boundaries of computation and the narratives we construct around it.

---