AI Infrastructure news and analysis on Web Pulse: 23786 curated articles tracking the latest AI Infrastructure developments, tools, and research, updated continuously from vetted sources.
AI agents need real email inboxes to receive verification codes, hold threads, and act as participants, not just senders. MailKite offers two architectures—bring-your-own agent or managed runs—with features like custom d…
MailKite offers a developer tool that gives AI agents an inbox to receive and reply to emails, addressing a gap in send-only email tools like Loops. The tool parses incoming emails as JSON and enables a receive→verify→th…
MailKite launches a Mailchimp Transactional (Mandrill) alternative designed for AI agents, offering a streamlined receive→reply loop with built-in auth verification and parsed JSON events, while Mandrill requires a paid …
MailKite launches an email API designed for AI agents, offering parsed JSON with SPF/DKIM/DMARC verification and a receive-reply loop, contrasting with Mailjet's Parse API which requires manual route setup and lacks a tr…
MailKite launches an email API designed for autonomous AI agents, offering a receive→reply loop with built-in SPF/DKIM/DMARC verification, contrasting with Brevo's marketing-focused platform that requires developers to r…
MailKite launches an email API designed for AI agents, offering parsed JSON inboxes and a receive-reply loop as an alternative to Mailgun's rule-engine-based inbound handling. The service targets developers building auto…
MailKite, a general email infrastructure platform, positions itself as an alternative to AgentMail for AI agents, offering inboxes on the user's own domain with no per-inbox cap. AgentMail remains a focused, well-funded …
Anthropic's Claude Mythos Preview autonomously discovered over 23,000 software vulnerabilities via Project Glasswing, while the open-source community launched cost-optimization tools for AI coding agents and enterprise A…
MailKite offers a serverless alternative to Postal for AI agent email inboxes, eliminating the operational burden of self-hosting a mail server. While Postal requires managing MariaDB, Caddy, DNS, TLS, IP warmup, and blo…
Onepilot and Blink Shell are iOS apps for managing servers, but they serve different purposes. Blink Shell is an open-source, Mosh-native terminal for manual SSH work, while Onepilot is an operations layer that deploys, …
Onepilot and Secure ShellFish offer contrasting approaches to AI agent management, with Onepilot focusing on deploying and supervising a fleet of AI coding agents on user-owned servers, while Secure ShellFish is a leadin…
Two Harvard dropouts raised $800 million to build AI data centers that consume vast amounts of energy and water, with a single GPT-4 training run using 50 gigawatt-hours of electricity and large inference clusters using …
Two former Harvard students, dissatisfied with expert claims that a dedicated inference chip is physically impossible, founded Etched and raised $800 million to build an ASIC for transformer model inference. The story hi…
Indirect prompt injection, ranked as OWASP's top LLM application risk (LLM01) for 2025, exploits the architectural reality that language models treat all tokens in a flat context stream as instructions, with no privilege…
The International Monetary Fund warns that the massive debt financing AI infrastructure poses a greater economic threat than an AI bubble, noting that 60% of planned data centers have not broken ground.
MailKite launched a service that gives AI agents their own email inboxes on custom domains, enabling autonomous email handling without IMAP or MIME parsing. Developers can either run agents themselves via webhooks or let…
Inference startup Wafer claims it achieved 80% of Nvidia B200 performance on AMD MI355X GPUs running GLM-5.2, with 2.6x cheaper hardware, by optimizing the software stack. The benchmark, published by Wafer, shows 2626 to…
Security expert Matthew Garrett warns that granting LLM agents access to sensitive resources like calendars and email creates severe credential leakage risks, as tokens stored on disk can be exfiltrated via git repos or …
A developer released mlx-serve, a native Zig server for MLX-format language models on Apple Silicon, enabling local, free, and private use of AI coding assistants like Claude Code. The server exposes OpenAI, Anthropic, a…
A new analysis of retrieval-augmented generation (RAG) systems argues that the optimal retrieval depth k* should be calibrated per pipeline stage and reliability axis, not guessed as a single hyperparameter. The author p…