Recently, various strategies for distributed training of large language models (LLMs) have been proposed.By categorizing them into basic strategies and composite strategies, we have discovered that existing basic strategies provide limited options in specific scenarios, leaving considerable room for optimization in training speed.In this paper, we rethink the impact of memory and communication costs on the training speed of LLMs, taking into account the impact of intra-and inter-group communication performance disparities, and then propose a new set of basic strategies named the \textbf{Pa}rtial \textbf{R}edundancy \textbf{O}ptimizer (PaRO).PaRO Data Parallelism (PaRO-DP) accelerates LLM training through refined model state partitioning and tailored training procedures.

Graph Neural Networks (GNNs) that are based on the message passing (MP) paradigm generally exchange information between 1-hop neighbors to build node representations at each layer. In principle, such networks are not able to capture long-range interactions (LRI) that may be desired or necessary for learning a given task on graphs. Recently, there has been an increasing interest in development of Transformer-based methods for graphs that can consider full node connectivity beyond the original sparse structure, thus enabling the modeling of LRI. However, MP-GNNs that simply rely on 1-hop message passing often fare better in several existing graph benchmarks when combined with positional feature representations, among other innovations, hence limiting the perceived utility and ranking of Transformer-like architectures. Here, we present the Long Range Graph Benchmark (LRGB) with 5 graph learning datasets: $\texttt{PascalVOC-SP}$, $\texttt{COCO-SP}$, $\texttt{PCQM-Contact}$, $\texttt{Peptides-func}$ and $\texttt{Peptides-struct}$ that arguably require LRI reasoning to achieve strong performance in a given task. We benchmark both baseline GNNs and Graph Transformer networks to verify that the models which capture long-range dependencies perform significantly better on these tasks. Therefore, these datasets are suitable for benchmarking and exploration of MP GNNs and Graph Transformer architectures that are intended to capture LRI.

Plus: Anthropic's new tools are freaking out the markets Every time OpenAI, Google, or Anthropic drops a new frontier large language model, the AI community holds its breath. It doesn't exhale until METR, an AI research nonprofit whose name stands for "Model Evaluation & Threat Research," updates a now-iconic graph that has played a major role in the AI discourse since it was first released in March of last year. The graph suggests that certain AI capabilities are developing at an exponential rate, and more recent model releases have outperformed that already impressive trend. That was certainly the case for Claude Opus 4.5, the latest version of Anthropic's most powerful model, which was released in late November. In December, METR announced that Opus 4.5 appeared to be capable of independently completing a task that would have taken a human about five hours--a vast improvement over what even the exponential trend would have predicted. But the truth is more complicated than those dramatic responses would suggest.

To some, METR's "time horizon plot" indicates that AI utopia--or apocalypse--is close at hand. The truth is more complicated. Every time OpenAI, Google, or Anthropic drops a new frontier large language model, the AI community holds its breath. It doesn't exhale until METR, an AI research nonprofit whose name stands for "Model Evaluation & Threat Research," updates a now-iconic graph that has played a major role in the AI discourse since it was first released in March of last year. The graph suggests that certain AI capabilities are developing at an exponential rate, and more recent model releases have outperformed that already impressive trend. That was certainly the case for Claude Opus 4.5, the latest version of Anthropic's most powerful model, which was released in late November.

He has said privately the deal was'non-binding'. He has said privately the deal was'non-binding'. What does the disappearance of a $100bn deal mean for the AI economy? Apparent collapse of Nvidia-OpenAI tie-up raises questions about circular funding and who will bear the cost of AI's expansion Did the circular AI economy just wobble? Last week it was reported that a much-discussed $100bn deal - announced last September - between Nvidia and OpenAI might not be happening at all.

Training modern large language models (LLMs) has become a veritable smorgasbord of algorithms and datasets designed to elicit particular behaviors, making it critical to develop techniques to understand the effects of datasets on the model's properties. This is exacerbated by recent experiments that show datasets can transmit signals that are not directly observable from individual datapoints, posing a conceptual challenge for dataset-centric understandings of LLM training and suggesting a missing fundamental account of such phenomena. Towards understanding such effects, inspired by recent work on the linear structure of LLMs, we uncover a general mechanism through which hidden subtexts can arise in generic datasets. We introduce Logit-Linear-Selection (LLS), a method that prescribes how to select subsets of a generic preference dataset to elicit a wide range of hidden effects. We apply LLS to discover subsets of real-world datasets so that models trained on them exhibit behaviors ranging from having specific preferences, to responding to prompts in a different language not present in the dataset, to taking on a different persona. Crucially, the effect persists for the selected subset, across models with varying architectures, supporting its generality and universality.

Moltbook is the chaotic future of the internet. The first signs of the apocalypse might look a little like Moltbook: a new social-media platform, launched last week, that is supposed to be populated exclusively by AI bots--1.6 million of them and counting say hello, post software ideas, and exhort other AIs to "stop worshiping biological containers that will rot away." Moltbook was developed as a sort of experimental playground for interactions among AI "agents," which are bots that have access to and can use programs. Claude Code, a popular AI coding tool, has such agentic capabilities, for example: It can act on your behalf to manage files on your computer, send emails, develop and publish apps, and so on. Normally, humans direct an agent to perform specific tasks.

Axiom says its AI found solutions to several long-standing math problems, a sign of the technology's steadily advancing reasoning capabilities. Five years ago, mathematicians Dawei Chen and Quentin Gendron were trying to untangle a difficult area of algebraic geometry involving differentials, elements of calculus used to measure distance along curved surfaces . While working on one theorem, they ran into an unexpected roadblock: Their argument depended on a strange formula from number theory, but they were unable to solve or justify it. In the end, Chen and Gendron wrote a paper presenting their idea as a conjecture, rather than a theorem. Chen recently spent hours prompting ChatGPT in the hopes of getting the AI to come up with a solution to the still unsolved problem, but it wasn't working.

Mistral's New Ultra-Fast Translation Model Gives Big AI Labs a Run for Their Money "Too many GPUs makes you lazy," says the French startup's vice president of science operations, as the company carves out a different path than the major US AI companies. Mistral AI has released a new family of AI models that it claims will clear the path to seamless conversation between people speaking different languages . On Wednesday, the Paris-based AI lab released two new speech-to-text models: Voxtral Mini Transcribe V2 and Voxtral Realtime. The former is built to transcribe audio files in large batches and the latter for nearly real-time transcription, within 200 milliseconds; both can translate between 13 languages. Voxtral Realtime is freely available under an open source license.

AI is driving unprecedented investment for massive data centers and an energy supply that can support its huge computational appetite. One potential source of electricity for these facilities is next-generation nuclear power plants, which could be cheaper to construct and safer to operate than their predecessors. We recently held a subscriber-exclusive Roundtables discussion on hyperscale AI data centers and next-gen nuclear --two featured technologies on the MIT Technology Review 10 Breakthrough Technologies of 2026 list . You can watch the conversation back here, and don't forget to subscribe to make sure you catch future discussions as they happen. Demis Hassabis, CEO of Google DeepMind, summed it up in three words: "This is embarrassing." Hassabis was replying on X to an overexcited post by Sébastien Bubeck, a research scientist at the rival firm OpenAI, announcing that two mathematicians had used OpenAI's latest large language model, GPT-5, to find solutions to 10 unsolved problems in mathematics.