AI Infrastructure news and analysis on Web Pulse: 35693 curated articles tracking the latest AI Infrastructure developments, tools, and research, updated continuously from vetted sources.
Salesforce and Anthropic expanded their 'Claudeforce' partnership, embedding Salesforce's CRM platform inside Anthropic's Claude AI with the new 'Salesforce in Claude' product, which includes 37 pre-built sales skills an…
Infisical has introduced Agent Vault, an HTTP credential proxy designed to secure AI agent tool calls by injecting credentials on the fly and enforcing least-privilege boundaries. The proxy intercepts outbound requests f…
OpenAI is experiencing multiple high-profile executive departures, including Greg Brockman and top data center executive Malone, following a reorganization of its infrastructure organization, according to TechCrunch. The…
Tata Communications reports that enterprises are deploying AI agents, voice AI, and automation across channels faster than their supporting architecture can coordinate, creating operational gaps between deployment veloci…
Salesforce and Anthropic announced a strategic partnership called Claudeforce, integrating Claude AI into Salesforce's enterprise platform to provide agentic experiences. The partnership launches with Salesforce in Claud…
A new guide from Honeycomb compares seven Datadog alternatives for AI and agent observability, highlighting cost predictability, investigation complexity, and OpenTelemetry portability as key factors. The guide evaluates…
Google has introduced Gemini Spark, a persistent agent designed to execute multi-step tasks in the background across devices, including workflows that start on mobile and continue on a macOS host. The capability, availab…
A developer demonstrates how to run AI models directly in the browser using ONNX Runtime Web, eliminating the need for server-side processing. The approach leverages WebAssembly and WebGPU to execute computer vision task…
Perplexity launched Portable Computer, a local version of its agentic AI software that runs on-device to keep data off the cloud by default, available initially to Pro and Max subscribers on Nvidia's DGX Spark desktop AI…
Enterprise AI agents require an escalation architecture rather than merely better prompts, according to an analysis of production system design. The piece argues that approval buttons fail because they lack structured co…
A new tool from an unnamed developer promotes serving Markdown versions of web pages to AI agents via HTTP content negotiation, using the `Accept: text/markdown` header to reduce token usage, improve retrieval signal-to-…
Meta's aggressive AI restructuring in 2026 has triggered employee backlash, including forced reassignments, keystroke surveillance, and 8,000 layoffs, while internal metrics show a 220% increase in code changes but only …
Buzz, an event-driven workspace where humans and agents share identity, history, code, and auditable actions, is examined through throughput, latency, capacity planning, backpressure, and cost. The project emphasizes typ…
Codebreaker Labs, a Boulder startup co-founded by Ryan Gill, filed its first SEC Form D on August 26, signaling a fundraising effort for its plan to manufacture experimental data for genomics AI, though the filing does n…
Anthropic has agreed to a roughly $45 billion, six-year cloud computing deal with UK-based AI infrastructure provider Nscale, one of the largest AI infrastructure agreements to date, according to reports. The agreement g…
Intel Corp. unveiled a three-pronged hardware strategy at the Hot Chips 2026 conference, positioning agentic AI as a system-level workload requiring CPUs, GPUs, memory, interconnects, and advanced packaging to work toget…
Amazon Web Services (AWS) announced Amazon Bedrock AgentCore evaluations, a new capability that decouples agent evaluation from the underlying framework by leveraging OpenTelemetry, enabling teams to evaluate agents buil…
Researchers proposed FIBER, a thread-register decoupled GPU execution model that extends the SIMT architecture to improve tensor computation efficiency, achieving a 2.25x end-to-end speedup on Ampere, 1.8x on Hopper, and…
Samsung presented a 16 GB LPDDR5X-PIM memory package at Hot Chips 2026 that delivers 614 GB/s of internal bandwidth to its own compute units, an eightfold increase over the 76.8 GB/s available through external pins, enab…
Token prices could be significantly lower, but inference companies are inflating them by renting GPUs and adding margins of over 40%, according to an unnamed analyst. These companies have current business because they st…