Full-text search across 68361 articles. Combine with topic and date filters; results sorted by relevance.
Mouse, an agent harness built on the OpenCode engine, scored 24/30 on the FrontierHarness benchmark, the highest pass rate among 13 harnesses tested with Kimi K3 on 30 coding tasks. Mouse passed 18/21 Terminal-Bench 2.1 …
A developer has created an open-source bridge that connects ChatGPT Web to local IDEs via the Model Context Protocol (MCP), allowing developers to offload heavy code-planning tasks to their ChatGPT Plus subscription whil…
Abliteration.ai, a startup selling hosted open-weight AI models with safety refusals removed, is now offering an abliterated version of Z.ai's GLM-5.3 and courting venture investors after funding cloud costs from custome…
Vercel's AI Gateway now offers Ling 3.0 Flash Sante, a health-focused Mixture-of-Experts model from inclusionAI with 124B total parameters and about 5.1B active per token, free through October 4. The model, designed for …
OpenAI's GPT 6 Astra model is now available on Vercel's AI Gateway, enabling developers to integrate the model for long-running agentic tasks such as software engineering, computer and browser use, and scientific researc…
SpaceXAI's Grok 4.6 is now available in public preview on Snowflake Cortex AI, delivering frontier intelligence for long-running agentic coding and knowledge work tasks within Snowflake's secure perimeter. The model, whi…
Cloudflare has launched early access to Vulnerability Discovery and Remediation, a new component of its Managed Defense suite that uses OpenAI's GPT-5.6 Cyber model to prioritize security fixes by combining code analysis…
Doberman, a security tool for coding agents, enforces guardrails on the execution path rather than relying on advisory prompt filters. The system routes every tool call through a fail-closed, raise-only decision engine t…
Meta released Muse Spark 1.3, its latest large language model, claiming it now matches OpenAI and Anthropic in performance, with Chief AI Officer Alexandr Wang saying it is competitive with Claude Fable 5.1 and better th…
Kestero, a new website widget service, launched on Hacker News with tools that let users describe a widget in plain language and have AI draft the code, or write HTML, CSS, and JavaScript manually, with all widgets runni…
Maneshwar, developer of LiveReview, a blast-radius aware AI code review tool, explains common failure modes in background job processing, focusing on the dual write problem where a process crash between database and queu…
Gigi Sehgal, founder of Gigi Sehgal LLC, argues that inadequate QA practices are leading to broken products, citing abysmal test coverage and a lack of security, integration, and stress testing. She emphasizes that in th…
Google launched Gemini 3.8 Flash, its third Flash model in six weeks, claiming flagship-level coding performance at lower cost, with CEO Sundar Pichai announcing the release. The model is priced at $0.75 per million inpu…
Cursor, the AI code editor developer, announced that its cloud agents can now run on self-hosted machines via Lambda MicroVMs, enabling teams to execute agents inside their own AWS accounts and networks. The company repo…
A developer introduced rgctl, a reachability graph control tool that indexes entire codebases to provide compact, deterministic blast-radius queries for AI coding agents. The tool precomputes reverse reachability on a co…
Google introduced Gemini 3.8 Flash and Gemini 3.8 Flash Cyber, its best reasoning and coding models yet, available at the same price as 3.7 Flash at $0.75 per million input tokens and $3.75 per million output tokens. Gem…
Google introduced Gemini 3.8 Flash and Gemini 3.8 Flash Cyber, its latest AI models, on March 12, 2025, claiming the Flash variant delivers significant improvements in coding and reasoning at the same price as its predec…
XBin, an open-source project at xbin.dev, introduces a self-modifying sandbox system that separates code and runtime environments to let AI agents build and manage mini-apps with strict permissions, encrypted filesystems…
A developer detailed a strategy for bringing observability to Google AI agents, moving from local trace trees to production monitoring via OpenTelemetry. The approach emphasizes capturing decision paths with spans and ev…
The SBX AI Evaluation Kit, an open-source Docker Sandboxes Mixin Kit, enables reproducible AI evaluation workflows by executing configured commands in isolated sandboxes and recording runtime evidence such as stdout, std…