Full-text search across 4762 articles. Combine with topic and date filters; results sorted by relevance.
An engineer tested Anthropic's Claude products—Claude Code, Claude Desktop, and Claude Cowork—and confirmed that all three use Client ID Metadata Document (CIMD) on user-initiated OAuth flows, contrary to some third-part…
OpenAI's GPT-5.6 Sol achieved the highest score on ReactBench v1 at 43.1%, a new benchmark for coding agents on realistic React tasks, while Anthropic's Claude Fable 5 scored 41.2% at 6.3 times the cost. ReactBench, buil…
Apache Spark 4.2 is now available in Databricks Runtime 19 Beta, introducing governed metrics, vector and top-K primitives, an Arrow-first Python path, first-class change data capture, and stronger streaming and operatio…
Databricks announced Thinking Machines Lab's open-weights model Inkling is now available on the Databricks platform through Unity AI Gateway, enabling enterprise customers to build agents and applications with coding and…
Anthropic's Claude Fable 5, a specialist model in a new tier above Opus, launched June 9, 2026, at double the Opus rate ($10 per million input tokens, $50 per million output) with always-on adaptive thinking and safety c…
Developers benefit from AI agents that work inside shared systems like code repositories, while other roles get high-maintenance tools that sit outside the workflow, according to a blog post on the topic of agent-native …
OpenAI has become one of the largest liabilities in recent economic history, with plans to burn over $852 billion by the end of 2030, according to the Where's Your Ed At newsletter. The AI bubble is driven by cult-like p…
The Skylight team at the Allen Institute for AI (Ai2) built Shippy, a maritime AI agent for real-time domain awareness, and learned that reliability—not the model—is the core challenge for high-stakes operational agents.…
0xPdf launched a pay-as-you-go pricing model for its schema-first PDF-to-JSON API, replacing monthly plans with a prepaid wallet system. The service offers a free first parse, a $5 welcome credit, and an MCP server for A…
Homebound, an open-source alpha-stage Django blog, lets users self-host their social-media history from Google+, Facebook, and Twitter/X, with full-text and semantic search, an MCP server for LLM integration, and a publi…
A developer compared Playwright MCP and Playwright CLI for use with Claude Code, finding that CLI uses approximately 26,000–27,000 tokens per multi-step UI test versus MCP's 114,000 tokens, a difference of nearly 90,000 …
Fin has published a curated set of Claude Code skills and hooks used by hundreds of its engineers, alongside a framework distinguishing effective from ineffective skills based on its internal experience. The company's pl…
Visual Studio 2026's July update (version 18.7.4, released July 14) adds real-time billing alerts and built-in Agent Skills to address Copilot usage-based billing shock after GitHub switched to metered pricing on June 1,…
Dex Horthy, CEO and cofounder of HumanLayer, coined the term 'context engineering' and shared lessons from building AI agents, including that shipping unread code leads to disaster within months after a July 2025 experim…
Emergent, an AI-powered coding platform founded in June 2025, has raised $130 million in Series C funding at a $1.5 billion post-money valuation, led by Creaegis with participation from Claypond Capital, Sentinel Global,…
NVIDIA released OpenShell, an open-source (Apache 2.0) secure runtime for AI agents that enforces controls at the environment layer rather than the model or application layer, preventing agents from overriding their own …
Reqable, a developer tool for API debugging, introduced MCP support in version 3.2, enabling AI agents like GitHub Copilot to control traffic capture, request analysis, and API testing. The open-source Reqable MCP server…
The value in AI has shifted from models to the inputs around them—training data, environments, and inference capacity—as model capability commoditizes rapidly, according to an industry analyst. This week's events, includ…
A developer argues that LLM agent harnesses should be modeled after the Unix/Linux environment, prioritizing determinism, minimal core prompts, and runtime skill loading to reduce cognitive load. The harness must provide…
A developer spent a month building linkedin-skills, an open-source system of ten AI-powered skills for Claude Code and Codex that automates the LinkedIn content grind—from planning and writing to engagement analysis—whil…