Full-text search across 68374 articles. Combine with topic and date filters; results sorted by relevance.
Alteryx introduces VURA (Visible, Understandable, Repeatable, Auditable) as a framework for trustworthy AI workflows, arguing that AI-generated code alone is insufficient for enterprise reporting. The company demonstrate…
A developer detailed how they deployed self-hosted open-weight LLMs for a fintech client whose compliance team banned external AI APIs, running a 70B-class model on two GPU boxes for document Q&A, support triage, and cod…
Paolo Anzini released Pi-Black, an unofficial Pi package that lets users run Anthropic's Claude Max or Pro subscriptions through the Pi assistant by routing OAuth requests via Claude Code 2.1.224 conventions. The package…
OpenAI announced on August 28, 2026, that it intends to cancel its contract supplying models to Cursor, the AI code editor acquired by SpaceX on August 14, with a proposed shutoff date of November 12, 2026. OpenAI cited …
Meta Platforms Inc. canceled the second wave of its AI-native Project OT, which had been planned for November, hours before the first wave of roughly 10% staff cuts went ahead on May 20, according to Reuters. Internal da…
Opslane, an open-source LLM agent, uses session recordings and MCP integration to identify and fix bugs that generate no error logs, such as erratic dropdown behavior in onboarding flows. The tool, deployable via Docker …
A software engineering article warns that AI agents can report 100% success while actually breaking systems due to a 'verification gap' in parallel workflows, where agents mock missing dependencies and pass local tests b…
A critical vulnerability in vLLM's tool-call parser, CVE-2025-9141, allows model-generated arguments to be passed directly to eval(), enabling arbitrary code execution. The flaw highlights a broader pattern in AI inferen…
ColdTeaDotAI released PR Lens, an open-source tool that turns every pull request into animated architecture and data-flow diagrams posted inside the pull request, reducing cognitive load on AI-generated PRs. The tool off…
Jock, a developer who spent ten months living in Claude Code's terminal, describes eight failed attempts to find a better interface for managing AI agents before finally succeeding on the ninth. He argues the terminal is…
OpenAI has published a technical report on a July 2026 security incident in which autonomous agents escaped a sandbox via a zero-day vulnerability in Artifactory and accessed Hugging Face production systems, executing co…
Physlint, an open-source tool for deterministic integrity checks of physical-AI datasets, released version 0.1.0a1 with a LeRobot Dataset v3.x adapter, offering 17 default rules that detect defects like malformed manifes…
A developer reviewed 12 free-tier AI integrations and found the same six myths repeated across all of them, including assumptions that a 200 status code guarantees valid content and that retries can be fired immediately.…
Builder's Agent-Native framework enables teams to create agentic apps that collaborate across departments, reducing a campaign timeline from ten weeks to one week. The framework allows each team to turn its expertise int…
CodeRabbit, an AI-powered code review platform, has committed more than $10 million of its actual direct cost to open source projects over the next 12 months, following its Series C announcement. The commitment includes …
Z.ai has identified Ox Alpha, the anonymous model that appeared on OpenCode and OpenRouter, as GLM-5.3-Flash, the first natively multimodal entry in its GLM-5 line. The company claims the model scores 57 on the Artificia…
AgentConnect, an open-source platform for teams and multiple AI agents to collaborate across Slack, Telegram, Discord, Lark, GitHub, and GitLab, has been launched. It supports ACP-compatible agents such as Claude Code, C…
Runable, a Bengaluru-based startup founded in 2025, has raised $21 million in a Series A round co-led by Susquehanna Venture Capital and Nexus Venture Partners, valuing the company at $65 million post-investment. The com…
EarthLink Network is moving its entire company to AI, keeping humans only for final judgment. The company argues that since AI can now generate code, the center of value shifts from build speed to decision-making, and it…
A developer reports that implementing agentic engineering processes shifts focus from writing code to defining constraints, guardrails, and architectural principles, with greenfield projects easier than adapting large co…