This paper has two goals. First, we present the turn-taking annotation layers created for 95 minutes of conversational speech of the Graz Corpus of Read and Spontaneous Speech (GRASS), available to the scientific community. Second, we describe the annotation system and the annotation process in more detail, so other researchers may use it for their own conversational data. The annotation system was developed with an interdisciplinary application in mind. It should be based on sequential criteria according to Conversation Analysis, suitable for subsequent phonetic analysis, thus time-aligned annotations were made Praat, and it should be suitable for automatic classification, which required the continuous annotation of speech and a label inventory that is not too large and results in a high inter-rater agreement. Turn-taking was annotated on two layers, Inter-Pausal Units (IPU) and points of potential completion (PCOMP; similar to transition relevance places). We provide a detailed description of the annotation process and of segmentation and labelling criteria. A detailed analysis of inter-rater agreement and common confusions shows that agreement for IPU annotation is near-perfect, that agreement for PCOMP annotations is substantial, and that disagreements often are either partial or can be explained by a different analysis of a sequence which also has merit. The annotation system can be applied to a variety of conversational data for linguistic studies and technological applications, and we hope that the annotations, as well as the annotation system will contribute to a stronger cross-fertilization between these disciplines.

Last month, the UK government announced the home for its new exascale supercomputer, designed to give the country an edge in the global artificial intelligence race. The £900 million ($1.1 billion) project would be built in Bristol, a city in the west of England famed for its industrial heritage, and the machine itself would be named after the legendary local engineer, Isambard Kingdom Brunel. The Brunel AI project should have been a big moment for another Bristolian export--Graphcore, one of the UK's only large-scale chipmakers specializing in designing hardware for AI. Valued at $2.5 billion after its last funding round in 2020, the company is trying to offer an alternative to the US giant Nvidia, which dominates the market. With AI fast becoming an issue of geopolitical as well as commercial importance, and countries--including the UK--spending hundreds of millions of dollars on building strategic reserves of chips and investing in massive supercomputers, companies like Graphcore should be poised to benefit.

A top AMD executive says that the company is thinking about deeper integration of AI across the Ryzen product line, but one ingredient is missing: client applications and operating systems that actually take advantage of them. AMD launched the Ryzen 7000 series in January, which includes the Ryzen 7040HS. In early May, AMD announced the Ryzen 7040U, a lower-power version of the 7040HS. Both are the first chips to include Ryzen AI "XDNA" hardware, among the first occurrences of AI logic for PCs. So far, however, AI remains a service that (aside from Stable Diffusion and some others) exclusively runs in the cloud.

Molecular property calculations are the bedrock of chemical physics. High-fidelity \textit{ab initio} modeling techniques for computing the molecular properties can be prohibitively expensive, and motivate the development of machine-learning models that make the same predictions more efficiently. Training graph neural networks over large molecular databases introduces unique computational challenges such as the need to process millions of small graphs with variable size and support communication patterns that are distinct from learning over large graphs such as social networks. This paper demonstrates a novel hardware-software co-design approach to scale up the training of graph neural networks for molecular property prediction. We introduce an algorithm to coalesce the batches of molecular graphs into fixed size packs to eliminate redundant computation and memory associated with alternative padding techniques and improve throughput via minimizing communication. We demonstrate the effectiveness of our co-design approach by providing an implementation of a well-established molecular property prediction model on the Graphcore Intelligence Processing Units (IPU). We evaluate the training performance on multiple molecular graph databases with varying degrees of graph counts, sizes and sparsity. We demonstrate that such a co-design approach can reduce the training time of such molecular property prediction models from days to less than two hours, opening new possibilities for AI-driven scientific discovery.

Graphcore is continuing to build out its AI applications and services ecosystem, launching a new partnership with AI platform company Pienso to make its powerful text analysis solution available on IPUs in the cloud. Pienso uses natural language processing to help businesses extract actionable insights from written text such as comments posted on social media, transcripts of customer service phone calls, news articles and documents. Pienso Graphcore is aimed at enterprise users such as media and entertainment companies, consumer internet - including social networks and e-commerce businesses, telecoms providers, and anyone trying to get high quality, high speed insights from large amounts of written data. No coding or ML skills are needed to build and run models in Pienso, meaning it can be used by subject matter experts and strategic decision makers within a business, removing reliance on in-demand AI engineers. Thanks to the IPU's designed-for-AI architecture and world leading performance in Natural Language Processing, Pienso runs considerably faster and with finer granularity and precision on IPUs than on other compute platforms; a performance gain that makes an already powerful solution truly transformative for its users.

For Twigfarm, a Seoul-based AI translation startup, success is a balancing act. The company's ambitious and important mission depends on its ability to deliver high-accuracy results as quickly as possible. At the same time, as a fast-growing business, operational expenses need to be carefully managed. When Twigfarm recently transitioned from GPUs to Graphcore's Intelligence Processing Units (IPUs) no price-performance trade-off was needed. Quite the opposite--switching to IPUs delivered a 10x performance gain, while simultaneously lowering costs.

AI-driven scientific research firm LabGenius is harnessing the power of Graphcore's IPUs (Intelligence Processing Units) to speed up its drug discovery efforts. LabGenius is currently focused on discovering new treatments for cancer and inflammatory diseases. The firm combines AI, lab automation, and synthetic biology for its potentially life-saving work. Until now, the company has been using traditional GPUs for its workloads. LabGenius reports that switching to Graphcore's IPUs in cloud instances from Cirrascale Cloud Services enabled its training of models to be reduced from one month to around two weeks.

In health care, the days of business as usual are over. Around the world, every health care system is struggling with rising costs and uneven quality despite the hard work of well-intentioned, well-trained clinicians. Health care leaders and policy makers have tried countless incremental fixes--attacking fraud, reducing errors, enforcing practice guidelines, making patients better "consumers," implementing electronic medical records--but none have had much impact. At its core is maximizing value for patients: that is, achieving the best outcomes at the lowest cost. We must move away from a supply-driven health care system organized around what physicians do and toward a patient-centered system organized around what patients need. We must shift the focus from the volume and profitability of services provided--physician visits, hospitalizations, procedures, and tests--to the patient outcomes achieved. And we must replace today's fragmented system, in which every local provider offers a full range of services, with a system in which services for particular medical conditions are concentrated in health-delivery organizations and in the right locations to deliver high-value care. Making this transformation is not a single step but an overarching strategy. We call it the "value agenda." It will require restructuring how health care delivery is organized, measured, and reimbursed. In 2006, Michael Porter and Elizabeth Teisberg introduced the value agenda in their book Redefining Health Care. Since then, through our research and the work of thousands of health care leaders and academic researchers around the world, the tools to implement the agenda have been developed, and their deployment by providers and other organizations is rapidly spreading. The transformation to value-based health care is well under way. Some organizations are still at the stage of pilots and initiatives in individual practice areas. Other organizations, such as the Cleveland Clinic and Germany's Schön Klinik, have undertaken large-scale changes involving multiple components of the value agenda. The result has been striking improvements in outcomes and efficiency, and growth in market share. There is no longer any doubt about how to increase the value of care. The question is, which organizations will lead the way and how quickly can others follow? The challenge of becoming a value-based organization should not be underestimated, given the entrenched interests and practices of many decades. This transformation must come from within.

The 3D stacking of chips has been the subject of much speculation and innovation in the past decade, and we will be the first to admit that we have been mostly thinking about this as a way to cram more capacity into a given compute engine while at the same time getting components closer together along the Z axis and not just working in 2D anymore down on the X and Y axes. It was extremely interesting to see, then, the 3D wafer-on-wafer stacking that AI chip and system upstart GraphCore has been working on with Taiwan Semiconductor Manufacturing Co had nothing to do making logic circuits more dense within a socket. This will happen over time, of course, but the 3D wafer stacking that GraphCore and TSMC have been exploring together and are delivering in the third generation "Bow" GraphCore IPU – the systems based on them bear the same nickname – is about creating a power delivery die that is bonded to the bottom of the existing compute die. The effect of this innovation is that GraphCore can get a more even power supply to the IPU, and therefore it can drop the voltage on its circuits and therefore increase the clock frequency while at the same time burning less power. The grief and cost of doing this power supply wafer and stacking the IPU wafer on top are outweighed by the performance and thermal benefits on the IPU, and therefore GraphCore and its customers come out ahead on the innovation curve.

We formulate seven fundamental principles of evolution that appear to be necessary and sufficient to render a universe observable and show that they entail the major features of biological evolution, including replication and natural selection. These principles also follow naturally from the theory of learning. We formulate the theory of evolution using the mathematical framework of neural networks, which provides for detailed analysis of evolutionary phenomena. To demonstrate the potential of the proposed theoretical framework, we derive a generalized version of the Central Dogma of molecular biology by analyzing the flow of information during learning (back-propagation) and predicting (forward-propagation) the environment by evolving organisms. The more complex evolutionary phenomena, such as major transitions in evolution, in particular, the origin of life, have to be analyzed in the thermodynamic limit, which is described in detail in the accompanying paper. Significance statement Modern evolutionary theory gives a detailed quantitative description of microevolutionary processes that occur within evolving populations of organisms, but evolutionary transitions and emergence of multiple levels of complexity remain poorly understood. Here we establish correspondence between the key features of evolution, renormalizability of physical theories and learning dynamics, to outline a theory of evolution that strives to incorporate all evolutionary processes within a unified mathematical framework of the theory of learning. Under this theory, for example, natural selection readily arises from the learning dynamics, and in sufficiently complex systems, the same learning phenomena occur on multiple levels or on different scales, similar to the case of renormalizable physical theories.