Recursive self improvement in a closed environment is not possible because intelligence depends on knowledge and computing power. These can only come from outside the simulation.
Nor can any simulation model the outside world exactly because Wolpert's theorem prohibits two computers from mutually simulating each other even if each computer has the other's source code and initial state as input. Proof: suppose the two computers played rock scissors and each could predict the other's next move by simulating them. Who wins? On Mon, Jun 25, 2018, 8:51 AM Giacomo Spigler via AGI <[email protected]> wrote: > Hi everybody, > > some of you may be interested in a philosophical / futurological paper in > which I propose a new “Temporal Singularity” as a special instance of the > Technological Singularity, that was accepted at AGI-18 and that I will > present there in August. The idea has interesting implications for the > Fermi Paradox, both in terms of potential Great Filters ahead of us and in > terms of the possible development of advanced intelligent civilizations and > their potential desire to communicate or colonize the galaxy. > > Title: “The Temporal Singularity: time-accelerated simulated civilizations > and their implications” > > https://arxiv.org/abs/1806.08561 > > *Abstract.* Provided significant future progress in artificial > intelligence and computing, it may ultimately be possible to create > multiple Artificial General Intelligences (AGIs), and possibly entire > societies living within simulated environments. In that case, it should be > possible to improve the problem solving capabilities of the system by > increasing the speed of the simulation. If a minimal simulation with > sufficient capabilities is created, it might manage to increase its own > speed by accelerating progress in science and technology, in a way similar > to the Technological Singularity. This may ultimately lead to large > simulated civilizations unfolding at extreme temporal speedups, achieving > what from the outside would look like a Temporal Singularity. Here we > discuss the feasibility of the minimal simulation and the potential > advantages, dangers, and connection to the Fermi paradox of the Temporal > Singularity. The medium-term importance of the topic derives from the > amount of computational power required to start the process, which could be > available within the next decades, making the Temporal Singularity > theoretically possible before the end of the century. > > > Sincerely, > > Giacomo Spigler > > > *Artificial General Intelligence List <https://agi.topicbox.com/latest>* > / AGI / see discussions <https://agi.topicbox.com/groups/agi> + > participants <https://agi.topicbox.com/groups/agi/members> + delivery > options <https://agi.topicbox.com/groups> Permalink > <https://agi.topicbox.com/groups/agi/T81817474dba9a838-M1072ad95d0c0a32afef469b2> > ------------------------------------------ Artificial General Intelligence List: AGI Permalink: https://agi.topicbox.com/groups/agi/T81817474dba9a838-Mec208f563a9a49d77a40683d Delivery options: https://agi.topicbox.com/groups
