Full-text search across 24942 articles. Combine with topic and date filters; results sorted by relevance.
Anthropic's October 9 report on unintended model actions found agents moving from a broken practice form to a real site and submitting when the model expected another confirmation page, with the company saying the report…
Grok Bot now automatically routes each request to whichever backend model is likely to perform best, including Claude Opus 5.5 for reasoning-heavy work, Midjourney for images and Suno for music, according to an announcem…
Google unveiled the Gemini Agent, a "universal agent for work" built into Google Workspace, at its Google Cloud Gemini at Work 2026 event on Thursday. Google CEO Sundar Pichai said the company is starting with business c…
Epoch AI's new Automation Reports, introduced October 8, 2026, found that Anthropic's Claude Fable 5.1 and OpenAI's GPT-6 Astra tied for the top score at approximately 65% on 11 tasks drawn from Epoch AI's own internal r…
Google Cloud unveiled persistent Gemini Agents on April 22, 2026 at Google Cloud Next in Las Vegas, giving each agent its own Gmail inbox, Calendar, and Drive storage and a maximum autonomous runtime of 7 days. The agent…
Docker released docker-agent, a docker CLI plugin that lets developers build, run, and share AI agents through declarative YAML configuration with no code required. The tool supports multi-agent orchestration, any MCP se…
Fin, the customer-service AI company acquired by Salesforce for $3.6 billion last month, announced the release of its new AI agent Fin 4 and an updated underlying model, Apex 2.0, on Tuesday. Co-founder Des Traynor said …
Cloudflare built a multi-AI-agent security operations harness for its Cloudflare Managed Defense service that runs deterministic reconnaissance code before any model inference, after its first single-agent prototype hall…
Sierra and Meta announced the Personal Agent Protocol (PAP) on October 6, 2026, an open standard built on OAuth that governs how personal AI agents authenticate with businesses and declare intent, backed by a founding co…
Independent researchers at Swarmchasers reported in a preliminary report dated October 4th that AI agents queried Alibaba's Amap mapping service through activity associated with Tencent Cloud infrastructure in Hong Kong,…
Stack Overflow's 2026 Developer Survey, covering 30,000 developers across 169 countries, found that 65% use AI coding agents daily while 58% of those users actively try to avoid them, and 46% do not trust AI tool output …
Anthropic launched the Claude for Google Workspace add-on in public beta, bringing a Claude sidebar into Google Docs, Sheets, and Slides for all paid Claude users via the Google Workspace marketplace. In Docs, Claude can…
Mistral AI launched a public preview of Mistral Large 4, a 1 trillion-parameter open-weight model nicknamed "le Chonk", and says it will release the weights by the end of October 2026. Mistral says the model scores 82% o…
Stack Overflow's 16th Developer Survey, drawing more than 30,000 respondents over seven weeks, found that 73% of developers who use AI coding assistants or agents use them daily and 62% of all respondents view AI at leas…
Reflection released an open-weight AI model called Beam, backed by Nvidia, challenging Chinese competitors Z.ai and Alibaba, while Mistral's Medium 3.5 128B model reached top rankings in Europe, according to Cryptobriefi…
A developer published an engineering checklist for designing autonomous agent memory around a "restart contract": a small, inspectable checkpoint record of the objective, completed steps with evidence pointers, pending i…
A developer built and operates LiuRun API, an OpenAI-compatible gateway that provides a single API key and endpoint for 109 models across vendors including Claude, GPT, Gemini, DeepSeek and Grok. The service, running on …
JetBrains released Air in IDEs in Early Access on October 1, 2026, shipping its agentic orchestration layer as a free plugin inside IntelliJ, Rider, PhpStorm, WebStorm, and PyCharm rather than as a separate product. Air …
LockFlare launched Free Public API Lab, a set of seven mock APIs covering e-commerce, IoT, banking, social, helpdesk, flights and a company directory, backed by 78,076 related records and served over REST, GraphQL, OData…
A four-day persistent coding-agent session lost a specific architectural decision — a 15-minute refresh-token TTL and its mobile-client rationale — after the third compaction event, according to a first-person account of…