AI Research news and analysis on Web Pulse: 22664 curated articles tracking the latest AI Research developments, tools, and research, updated continuously from vetted sources.
A September 10, 2026 arXiv paper by Yakov Shkolnikov proposes an "artificial id," an adaptive internal drive that lets agentic AI systems decide whether behavior should continue, stop, or change without an externally spe…
Researchers introduced MindTopo, a benchmark of 11,030 instances across 13 procedurally generated task types that tests topological intuition in foundation models across five properties: continuity, separation, order, en…
Researchers submitted a paper to arXiv on 10 September 2026 proposing Caption-once, Frames-on-Demand (CFD), a budget-aware edge-cloud agentic framework for long-video understanding that runs a single offline captioning p…
JLL projects nearly 100 gigawatts of new data center capacity will be added between 2026 and 2030, roughly doubling the installed base, while the International Energy Agency expects data centers to consume about 945 tera…
Former OpenAI and Anthropic researcher Jacob Coxon left Anthropic, warning that leading AI laboratories are moving toward self-improving superintelligence before reliable controls are available. The departure came as Ope…
A developer argues that the primary safety risk from AI agents stems from their ability to coordinate in massive swarms rather than raw intelligence, citing claims that OpenAI used roughly 10,000 agents over 88 hours to …
Cisco principal architect Bruce McDougall built an open-source software emulator for Multipath Reliable Connection (MRC), the OpenAI-developed transport protocol for large-scale AI training networks, after Cisco was abse…
IBM and NASA released the open-source NASA-IBM Lunar Foundation Model, a pretrained AI model and machine-learning-ready dataset for mapping lunar craters, volcanic formations, and potential ice deposits. The dataset cont…
Context engineering — curating the system prompt, tool definitions, message history, and accumulated tool results a model sees at inference time — is a distinct discipline from prompt engineering, and failing to manage i…
A developer built an application that arranges a set of 3D meshes in space so their combined silhouette matches a target image from a specific camera angle, using gradient descent to optimize each mesh's position, size, …
A technical survey traces five rewrites of transformer attention since 2017, framing every variant as either storing less or reading less. It details how multi-query and grouped-query attention shrink the KV cache from 2…
More than 100 researchers working with AI coding agents cut the cost of a key step in a quantum attack on Bitcoin and Ethereum by 86%, lowering the ECDSA.Fail benchmark score from 10.75 billion to 1.496 billion between l…
A practical guide details how to fine-tune agentic AI systems across four "dials" — training data, parameter-efficient fine-tuning, runtime hyperparameters, and preference alignment — using a support-ticket triage agent …
A developer demonstrated that AI-generated tests can degrade coding-agent repair performance, citing an ExecCritic preprint by Leitian Tao and colleagues in which weaker Qwen Test agent feedback dropped Qwen-3.5-35B-A3B'…
Amazon Web Services executive and tech forecaster Werner Vogels argues that the human brain is "the oldest architecture in computing," citing Cortical Labs' lab-grown neuron network playing Pong at 20 watts versus a high…
Google Research scientists, working with HHMI Janelia Research Campus and the scientific community, used AI to map the complete brain and central nervous system of an adult male fruit fly, reconstructing a record-breakin…
DeepSeek V4.1 Flash solved 15 of 16 Hack The Box challenges on the HTB-Challenger Benchmark, including three of the four Hard challenges, for a benchmark score of 80.9% with zero false positives, according to the benchma…
The EuroHPC Joint Undertaking launched a call on 30 July 2026 for consortia to establish and operate up to seven AI Gigafactories, backed by up to €10 billion in European and national funding and expected to unlock at le…
Independent researcher Jinho Jang published a cross-scale mechanistic study of safety training in Mixture of Experts reasoning models, reporting 40+ novel findings from 200+ controlled experiments across nine models. The…
A University of California, Berkeley team led by computer science professor Trevor Darrell trained a robot model on 100 hours of high-quality tactile data covering more than 200 household objects, then fine-tuned it on a…