AI Infrastructure news and analysis on Web Pulse: 12088 curated articles tracking the latest AI Infrastructure developments, tools, and research, updated continuously from vetted sources.
Zhipu, the Beijing-based AI company behind the GLM large language models, raised $4 billion in a Hong Kong share placement on July 8, 2026, at a 13% discount to its previous close, just six months after its IPO. The stoc…
Hugging Face silently moved Docker Space deployments behind a PRO subscription paywall, with users reporting that the Docker SDK is now marked as "Paid" in the UI and CLI deployments return errors requiring a PRO subscri…
MonkeyCode, an open-source project, argues that developers are not achieving 10x productivity with AI because they rely on chat-based interactions rather than building a repeatable, collaborative, and verifiable AI devel…
OpenAI released GPT-5.6 in three tiers: Sol (high-end), Terra (mid-range), and Luna (budget). A developer argues that mainstream models now exceed what most developers can use, and that the real bottlenecks are lack of p…
Singapore's sovereign wealth fund Temasek plans to increase its AI investment exposure from 6% to 15% of its $400 billion portfolio by 2031, targeting areas including energy, data centers, semiconductors, cloud services,…
U.S. restrictions on top AI systems are driving developers and buyers toward open-source AI models, local deployment, and multi-provider strategies, according to The Hindu. The shift is linked to White House support for …
OpenAI retired Advanced Voice Mode on July 8 and replaced it with GPT-Live, a full-duplex voice model that processes input while generating output, enabling natural interruptions and backchannels. The system delegates co…
Meta broke ground on its first Canadian data center in Sturgeon County, Alberta, investing over CAD $13 billion in a 1-gigawatt facility optimized for AI workloads. The project is expected to create more than 3,000 const…
Cloudflare is rolling out new rules for 'mixed crawlers' that can be used for both search and AI training, setting a Sept. 15 deadline to block training and agent use by default on ad-supported pages. The move, a year af…
OpenAI is expanding its advertising pilot to France, Germany, and Ireland, hiring regional managers and client partners in Paris, Munich, and Dublin. The move follows its UK launch and aims to cover Europe's three larges…
Cloudflare announced new AI traffic controls that will treat mixed-use crawlers according to all of their behaviors, allowing publishers to block bots used for both search and training when a site blocks training, with t…
Researchers propose MiLSD, a micro line-segment detector designed for resource-constrained devices such as microcontrollers, achieving competitive accuracy within a one-megabyte memory budget. The detector uses a compact…
A new study from Writer finds that orchestration design, specifically the Writer Agent Harness, reduces enterprise agentic AI costs by 41% and tokens per task by 38% while maintaining quality, outperforming model swaps a…
Researchers developed a multi-analyst LLM pipeline that converted 68 public physiological corpora into 436 unique candidate rule shapes for contactless monitoring detectors, with 94 build-now components identified after …
Researchers propose ROAM, a framework that uses LLM reasoning to adapt frozen specialist models to new scenarios without retraining, reducing MAE by over 20% in industrial processes with minimal overhead.
Researchers propose Dynamic-in-Few-Step, a post-training acceleration framework that integrates dynamic structural sparsification into few-step distillation for video diffusion models. The method transforms a pre-trained…
Researchers proposed a hardware-aware pruning and quantization strategy for Graph Convolutional Neural Networks to adapt them for embedded FPGA platforms in event-based vision. The method achieved BRAM memory reductions …
Researchers introduced TF-Engram, a train-free memory system that stores phrase-specific semantic knowledge offline across GPU, DRAM, and SSD tiers, and uses predictive prefetching to reduce latency. In tests with Qwen3-…
Researchers propose DeLS-Spec, a speculative decoding method that decouples long- and short-context experts to accelerate LLM inference. By adding a lightweight local head to the existing DFlash model, DeLS-Spec achieves…
Researchers at an undisclosed institution found that in hierarchical search agents using large language models, scaling the delegation role improves exact match by ~11 points while scaling execution only improves by ~2.6…