Temporal heterogeneous networks (THNs) are evolving networks that characterize many real-world applications such as citation and events networks, recommender systems, and knowledge graphs. Although different Graph Neural Networks (GNNs) have been successfully applied to dynamic graphs, most of them only support homogeneous graphs or suffer from model design heavily influenced by specific THNs prediction tasks. Furthermore, there is a lack of temporal heterogeneous networked data in current standard graph benchmark datasets. Hence, in this work, we propose DURENDAL, a graph deep learning framework for THNs. DURENDAL can help to easily repurpose any heterogeneous graph learning model to evolving networks by combining design principles from snapshot-based and multirelational message-passing graph learning models. We introduce two different schemes to update embedding representations for THNs, discussing the strengths and weaknesses of both strategies. We also extend the set of benchmarks for TNHs by introducing two novel high-resolution temporal heterogeneous graph datasets derived from an emerging Web3 platform and a well-established e-commerce website. Overall, we conducted the experimental evaluation of the framework over four temporal heterogeneous network datasets on future link prediction tasks in an evaluation setting that takes into account the evolving nature of the data. Experiments show the prediction power of DURENDAL compared to current solutions for evolving and dynamic graphs, and the effectiveness of its model design.

A COMPUTER from 1973 has made chillingly accurate apocalyptic predictions and showed that civilisation as we know it could cease to exist by 2050. The eerily precise modelling was developed by professors at MIT university to predict how modern civilisation would behave by 2060 - and the findings have been as startling as they've been accurate. Dubbed "World One", the programme, commission by the Club of Rome, models how well the world can sustain its then growth trajectory. What it predicted was that by 2040 there would be a total global collapse if population and industries continued to grow unabated. The computer programme analysed troves of data on pollution levels, birth rates, and natural resource stocks to give an overall quality of life assessment.

Last Sunday we reported on the computer program that inventor George Davila Durendal, hoped (or so he said) would--for millennia--be a sort of Scripture for robots and people. The program constructs "prophecies" from the text of the King James Version, a translation of the Bible into English completed in 1611, which has remained influential for centuries. Will the A.I. Jesus version do so well? Not if you go by prophecies like this: "And he shall come against him, and said, As the LORD liveth, that he might be fulfilled which was spoken, he said, Thou are the spirit of your good works that ye have not seen, nor any thing of the service thereof, and a certain censer, and the sin offering, and the posts thereof were displeased with the dead of her father's house." If this is the best AI can do in 2020, you do not need to fear the Omega Point in your generation!

An artificial intelligence engineer has created an intriguing algorithm that learned human language from reading "the bible and nothing else" and is now churning out ominous prophecies based on the Holy Book. George Davila Durendal, a childhood coding prodigy and current AI engineer and entrepreneur, recently unveiled his wackies creation yet, an A.I. algorithm trained solely on the King James Bible and dubbed "AI Jesus". Described by Durendal himself as an "A.I. clone of Jesus", the software is a Boltzmannian natural-language processing model that "tries to replicate the style of the King James Bible without quite copying it". Designed to write about 3 different topics – 'The Plague', 'Caesar' and'The End of Days' – using the language of the Bible, AI Jesus has so far come up with some pretty scary, if somewhat nonsensical, prophecies… "The Plague shall be the fathers in the world; and the same is my people, that he may be more abundant in the mouth of the LORD of hosts," one of the phrases produced by AI Jesus reads. "And he shall come against him, and said, As the LORD liveth, that he might be fulfilled which was spoken, he said, Thou are the spirit of your good works that ye have not seen, nor any thing of the service thereof, and a certain censer, and the sin offering, and the posts thereof were displeased with the dead of her father's house," another prophecy states.

An artificial intelligence algorithm that churns out scripture is putting an interesting new twist on the Bible. The project, aptly dubbed AI Jesus by engineer and quantum researcher George Davila Durendal, is a language-processing algorithm that was trained exclusively on the King James Bible, according to Durendal's blog post. Needless to say, the 30,000-word algorithmic text includes some real Old Testament-style brutality. Durendal's algorithm wrote scripture about three topics: "the plague," "Caesar," and "the end of days." So it's not surprising that things took a grim turn.

An engineered created'AI Clone of Jesus' by feeding artificial intelligence the King James Bible, resulting in interesting and somewhat horrifying scriptures. George Durendal used a natural-language processing system to replicate the ancient words without exactly copying the text. The technology was programmed to write about three topics: 'the plague,' 'Caesar,' and the end of days.' The full copy of the AI's scripture is riddled with glitches, half of the nouns used are'Lord,' but some eerily resemble what is shown in the bible. An engineered created'AI Clone of Jesus' by feeding artificial intelligence the King James Bible, resulting in interesting and somewhat horrifying scriptures.