I took a look at the book on neutrosophy. It's a collection of papers but I just read the abstracts. It deals with reasoning under uncertainty about the degree of uncertainty, which should have some applications to AI. When predicting the next token in an LLM or text compressor you need to reduce a probability distribution of probabilities to a single number. We use ad hoc methods to do this. It wasn't obvious from the abstracts whether there is a more principled method.
-- Matt Mahoney, [email protected] On Thu, Jun 25, 2026, 8:32 PM John Rose via AGI <[email protected]> wrote: > On Tuesday, June 23, 2026, at 3:55 PM, Matt Mahoney wrote: > > Therefore, I define the friendliness of AI to be the rate of entropy > removed by replicating entities, measured in bits per second. A bit is at > least kT ln 2, or about 3 x 10^-21 J at room temperature. > > > On Thursday, June 25, 2026, at 6:38 PM, Matt Mahoney wrote: > > We don't have to worry about a fast takeoff because intelligence is not a > scalar quantity. You can't compare human and machine intelligence with a > single number like IQ. There is no "human level" threshold to cross to > launch a singularity. > > > There may be a way to practically estimate and track your definition of > friendliness in agents but I would use an overlay such as neutrosophy since > adding entropy might be required for some cases of situational > friendliness: > > https://zenodo.org/records/20562234 > *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/agi/subscription> > Permalink > <https://agi.topicbox.com/groups/agi/Teedaf4a19e56877e-M904a5d714915aa9f365bd59f> > ------------------------------------------ Artificial General Intelligence List: AGI Permalink: https://agi.topicbox.com/groups/agi/Teedaf4a19e56877e-M8fa3df96286560d2bbd16d9a Delivery options: https://agi.topicbox.com/groups/agi/subscription
