Introducing Claude Fable 5.2 and Claude Mythos 5.2
Our most capable models for daunting technical work, Claude Fable 5.2 and Claude Mythos 5.2 set a new bar in coding, finance, and the sciences.
AI NEWS JOURNAL
Search AI news
Search headlines, summaries and articles to connect the dots.
ResServe: Accurate and Efficient FP4 LLM Inference with Residue Compensation
arXiv:2611.08713v1 Announce Type: new Abstract: Block-scaled 4-bit floating-point (FP4) quantization reduces large language model inference costs but can degrade task quality. Higher-precision computation can mitigate this loss at the expense of some of the efficiency gains from FP4 inference. Narrow matrix computations common in decoding often leave spare hardware capacity for low-cost precision recovery. ResServe combines an FP4 activation base with an FP4-quantized residue representing information lost during quantization. It uses this spare capacity to compute the residue's contribution and combines results on-chip, avoiding extra result transfers. We apply this principle to linear layers and decode attention, while selective compensation limits added work when processing input prompts. On NVIDIA B200, compensated linear kernels using the NVFP4 format improve numerical precision while retaining latency close to uncompensated execution for the evaluated operations with few rows. In the evaluated NVFP4 inference configurations, ResServe adds at most 3.4% request-latency overhead over W4A4 and reduces request latency by 22.4-53.3% relative to W4A8. Across five models, code-generation accuracy improves over same-format uncompensated inference, with mean relative gains of 15.04% for NVFP4 and 53.57% for MXFP4.
NUMA-Torch: Compiler-Driven NUMA-Aware LLM Prefill on Multi-Socket CPUs
arXiv:2611.07105v1 Announce Type: new Abstract: For sufficiently large transformer-based Large Language Models (LLMs), whose parameters cannot be retained in on-chip caches, prefill throughput on multi-socket CPUs is often limited by sustainable DRAM bandwidth rather than peak floating-point throughput. In the standard PyTorch compilation (i.e., TorchInductor) path, model weights are allocated without considering the Non-Uniform Memory Access (NUMA) topology: specifically, the affinity between memory banks and compute cores is disregarded. This causes a substantial fraction of weight accesses to traverse the inter-socket interconnect, severely degrading the effective memory bandwidth available to each socket. We address this bottleneck through a compiler-level solution that makes TorchInductor NUMA-aware. Treating each NUMA socket as an independent tensor-parallel partition, we introduce NUMA-aware Tensor Parallelism (NUMA-TP). This approach transparently shards weights across sockets and schedules compute kernels such that thread pools and memory allocations remain strictly local to their respective sockets using CPU affinity. We evaluate the approach on GPT-2 (117M, 345M, 762M) and BERT (Small, Large), which exercise standard multi-head attention and MLP, as well as Gemma 3 270M, which combines Multi-Query Attention with a GeGLU-gated MLP. By strictly enforcing data locality, our approach successfully mitigates cross-socket traffic, achieving prefill speedups of up to 2.63x on a dual-socket Haswell platform, up to 1.87x on a dual-socket Cascade Lake platform, and up to 2.27x on a four-socket Haswell-EX platform.
When Every Choice Is Correct: A Causal Study of Numerical Preference in Language Models
arXiv:2611.06025v1 Announce Type: new Abstract: When a language model chooses a number between 1 and 30, every integer in the range is valid, yet the model can favor particular answers. We use numerical choice to study how preference is processed across layers and tokens. Perturbation probing and gradient attribution nominate neurons for activation interventions. In a selected Qwen3-4B case, a pre-answer edit changes 17 to 15 while both runs first emit 1. After the edit ends, selective cache and attention-output replacements trace part of its continuing influence on the second digit. Replacing one attention head's output or the other heads' outputs jointly produces similar immediate readout contributions; both interventions restore 17 but have different final log-odds effects on 7 versus 5. Holding later multilayer perceptron (MLP) outputs at their values from the edited run without either replacement reduces this effect gap from 0.119 to 0.0025 nat. Later computation therefore changes how similar local contributions affect the continuation. Retrospective estimates across eighteen contexts capture much of the probability movement but miss the selected answer switch. Prompt tests also separate influence from answer changes: one held-out prompt retains influence without switching, and only one of twelve fresh wordings qualifies for the reader/MLP test; there, joint MLP clamping again reduces the gap between the two reader effects while the answer remains 17. These results use numerical choice as a controlled case for studying persistent state and conditional downstream processing; they do not establish the origin or a complete circuit of natural numerical preference.
A thousand fewer paths to root
OpenAI built an autonomous pipeline that found, validated, and generated patches for 948 local privilege-escalation vulnerabilities in the Linux kernel.
Co-Occurrence Priors Override Visual Spatial Evidence: Understanding False Alarms in Vision-Language Models for Construction Struck-By Hazard Detection
arXiv:2611.04112v1 Announce Type: new Abstract: Vision-language models (VLMs) increasingly support construction hazard monitoring, yet their frequent false alarms remain poorly understood. This study investigates whether false struck-by hazard warnings arise from failures in object recognition, spatial relation encoding, or hazard decisions dominated by learned co-occurrence priors. We evaluated Qwen2.5-VL-7B and InternVL3.5-8B using 355 counterfactual worker-excavator scene pairs with controlled spatial proximity and worker-removal variants, combining behavioral analysis, internal representation probing, causal interventions, and decision correction. Both models recognized the entities and encoded their spatial relations (out-of-fold AUROC: 0.82 and 0.91), assigning higher hazard scores to near than far scenes in 79% and 73% of pairs. Nevertheless, 74% and 100% of far scenes were falsely classified as hazardous. Removing the worker reduced Qwen's hazard rate to 11%, while worker presence exerted 2.4- and 3.2-times greater influence on hazard scores than spatial proximity in the respective models. Attention-head interventions, neuron-level interventions, and activation steering failed to eliminate this co-occurrence bias. However, conditioning hazard decisions on the model's own spatial-relation representation improved Qwen's specificity from 0.36 to 0.58 at matched sensitivity, outperforming threshold recalibration. These findings reveal that VLM struck-by false alarms stem primarily from decision-making failures rather than deficiencies in object recognition or spatial encoding, suggesting that future efforts should prioritize conditioning hazard decisions on encoded spatial evidence rather than further improving visual recognition alone.
As AI agents reshape the web, Google opens Gemini and Search to more apps
A new developer platform will let businesses bring their services to Google's AI experiences, potentially changing how consumers discover and use apps.
Polymathic AI and Princeton Researchers Release FlashMap, a Flow Map Drafter for 6.14x Faster LLM Decoding
FlashMap is a speculative decoding drafter from Polymathic AI, Princeton and USC ISI researchers. It drafts 16 tokens jointly in one pass and reaches up to 6.14x lossless speedup on Qwen3-8B. The post Polymathic AI and Princeton Researchers Release FlashMap, a Flow Map Drafter for 6.14x Faster LLM Decoding appeared first on MarkTechPost.
Causal Localization of Evidence Effects in Transformers
arXiv:2610.36524v1 Announce Type: new Abstract: Can controlled symbolic inputs reveal attention heads that influence a language model's decisions from natural language evidence? We introduce controlled evidence aggregation (CEA), which varies the counts and order of two symbols in otherwise fixed prompts and measures changes in a frozen Transformer's preference between two answer tokens. The preference is measured by their logit difference; the prompts prescribe no correct answer. Balanced utility causal selection (BUC) identifies compact head sets by jointly evaluating how much ablating their outputs removes the count effect and how closely patching mean outputs between count conditions recovers the effect in both directions. We derive conditional bounds linking head attribution to interv
A Quantitative Approach to Asch Conformity in Frontier Large Language Models
arXiv:2610.36668v1 Announce Type: new Abstract: The Asch conformity experiment has recently gained considerable attention as a way of measuring conformity in large language models (LLMs). While previous studies have focused on demonstrating conformity in LLMs, our work adds a further quantitative layer to this approach. Instead of sampling a frontier LLM on a suite of questions, our approach samples a single question repeatedly, leveraging the probabilistic nature of LLMs to produce a distribution of answers. In doing so, we can compare the distributions of answers before and after the model is presented with the manufactured consensus. Our experiments confirm that frontier LLMs do conform, reinforcing prior literature, and, through our distribution-to-distribution comparisons, provide add
How Anthropic ships Claude with Claude: Separating the Brain from the Hands
Katelyn Lesse and Angela Jiang on Opus 5.5, the Claude Platform, and the engineering behind AI agents.
From Large Language Models to World Models
Yan Deli, a senior expert at Tencent: LLMs are probabilistic models. They do not truly understand language; rather, they predict the next token (Next Token Prediction). Essentially, they are monotonous “word-chain” machines—moving forward one step at a time without retracing their path. At their core, LLMs are probabilistic models that learn, from statistical co-occurrence patterns, “what often appears alongside what,” and output “this is usually the case,” without grasping “why it is so.”...
HyScale: Scaling Long-Context Training for Learned Sparse Attention
arXiv:2610.32057v1 Announce Type: new Abstract: We present HyScale, a long-context training system for learned sparse attention. Learned sparse attention is a promising architecture for million-token contexts, widely adopted in production since DeepSeek-V3.2. Selection, however, grows into the training bottleneck. For each query, it scores every previous token whereas sparse attention reads only $k$; worse, current systems materialize a full score table and repeat selection during recomputation. Our key insight is that the output of selection is not an activation, but rather a set of indices. Building on it, HyScale introduces HyTopK and selection replay. HyTopK finds each query's exact top-$k$ on the fly without a score table, while selection replay reuses forward-pass selection in recomp
Nanbeige Releases Nanbeige4.3-33B, a 33B Open Agentic Coding Model
Nanbeige LLM Lab released Nanbeige4.3-33B, a 33B dense Apache 2.0 model with 512K context. It reports 80.9 on Terminal-Bench 2.1 and will teach the upcoming Nanbeige4.3-3B. The post Nanbeige Releases Nanbeige4.3-33B, a 33B Open Agentic Coding Model appeared first on MarkTechPost.
Hugging Face Releases Carbon-X, a 14B Open DNA Language Model that Brings DNA and Natural Language Together for the First Time
Hugging Face released Carbon-X, an open 14.8B DNA language model built on Qwen3-14B. It reads raw DNA in chat, answers in English, and averages 66.7% across 5 DNA benchmarks under Apache 2.0. The post Hugging Face Releases Carbon-X, a 14B Open DNA Language Model that Brings DNA and Natural Language Together for the First Time appeared first on MarkTechPost.
Claude Mods: The first implementation of an attention interface, a human-programmable agent interaction layer
Claude Mods is Anthropic’s programmable plugin system for Claude Code, representing an early form of the “Attention Interface”—it shifts the traditional machine-oriented agent harness toward a customizable interaction layer centered on human attention. Users can write Mods in TypeScript/JS or have Claude generate them automatically using natural language, thereby determining when to be interrupted, what content to see, and what decisions to make.
Claude Mods: A programmable attention interface that reshapes the collaboration paradigm between humans and AI agents
Claude Mods is a programmable plugin system for developers launched by Anthropic, marking a shift of the ‘agent harness’ from a machine-side interface to a human-side interface—namely, the ‘Attention Interface’. It enables users to customize Claude Code’s behavior, rendering, and interaction logic via TypeScript/JavaScript, thereby facilitating co-design workflows between humans and AI. This mechanism has already been applied to built-in features (such as You Should Know) and supports users in building plugins themselves or having them generated with Claude’s assistance.
Qwen2.5-1M: Deploy Your Own Qwen with Context Length up to 1M Tokens
Tech Report HuggingFace ModelScope Qwen Chat HuggingFace Demo ModelScope Demo DISCORD Introduction Two months after upgrading Qwen2.5-Turbo to support context length up to one million tokens, we are back with the open-source Qwen2.5-1M models and the corresponding inference framework support. Here’s what you can expect from this release: Opensource Models: We’re releasing two new checkpoints, Qwen2.5-7B-Instruct-1M and Qwen2.5-14B-Instruct-1M, marking the first time we’ve upgraded our opensource Qwen models to handle 1M-token contexts.
Qwen1.5-MoE: Matching 7B Model Performance with 1/3 Activated Parameters
GITHUB HUGGING FACE MODELSCOPE DEMO DISCORD Introduction Since the surge in interest sparked by Mixtral, research on mixture-of-expert (MoE) models has gained significant momentum. Both researchers and practitioners are keenly interested in understanding how to effectively train such models and assessing their efficiency and effectiveness. Today, we introduce Qwen1.5-MoE-A2.7B, a small MoE model with only 2.7 billion activated parameters yet matching the performance of state-of-the-art 7B models like Mistral 7B and Qwen1.