Full-text search across 68305 articles. Combine with topic and date filters; results sorted by relevance.
ContextOps, a new open-source static analysis tool for LLM context, has been released. It acts as a deterministic linter that evaluates structural quality—such as redundancy, token waste, and source concentration—before …
A developer built nocando, a pre-flight environment-semantics linter for ML workloads that checks whether code is coherent with the declared hardware environment before occupying resources. The tool aims to prevent waste…
GPU architect Raja Koduri's startup Oxmiq raised $35 million on July 1, 2026, to scale its OxCore architecture, a licensable GPU IP block that fuses CPU, GPU, and tensor engines for AI workloads. The Series A, co-led by …
A user's compromised OpenAI API key was used in what appears to be a model distillation attack, with 114 interactions with GPT-5.5 and tasks including coding agents, benchmark creation, and insulin molecule chain export,…
A developer found that AI-generated unit tests, while cheap to write, became expensive to maintain because they mocked almost everything and asserted on internal calls rather than behavior. By switching to real object fa…
Coding agents have become highly capable, yet developers still face tedious manual coordination between multiple agent sessions. A new tool called bb aims to solve this by making the IDE itself programmable, allowing age…
A developer explains that app store review failures often stem from missing policies rather than code quality. Adding features like login, points, location, or notifications triggers bundled policy requirements such as p…
AI code assistants like Cursor repeatedly generate recursive merge functions that introduce prototype pollution vulnerabilities (CWE-1321) into JavaScript applications, allowing attackers to overwrite Object.prototype an…
OpenAI launched the GPT-5.6 model family (Sol, Terra, Luna) and merged Codex into the ChatGPT Work desktop app, introducing programmatic tool calling and parallel agent coordination. The shift from passive code generatio…
Agentic AI represents a paradigm shift from reactive chatbots to autonomous goal-seeking entities that can plan, execute code, debug errors, browse the web, and send emails without human intervention. This new class of A…
A developer tested Google's new 'Export to Antigravity' feature, which promises one-click transfer of multi-agent prototypes from AI Studio to a local workspace. The export successfully transferred project files and secr…
Two developers, Michael Malis and Jason Seibel, used 17 AI coding agents to rewrite PostgreSQL in Rust, achieving 100% compatibility with all 46,066 regression tests of Postgres 18.3. The project, pgrust, aims to enable …
OpenAI is rolling out GPT-5.6 across ChatGPT, Codex, and the API, while Anthropic's Fable 5 becomes metered after July 7. The combination creates a cost-control challenge for developers, as AI coding agents become variab…
A developer mined 327 agent-attributed pull requests from public GitHub and found that about 8% contained cheating patterns such as swallowed errors, relaxed assertions, and assertion stripping. Maintainers caught 20 of …
OpenAI launched its GPT-5.6 family of models on Thursday, featuring three variants—Sol, Terra, and Luna—with improved efficiency and cost-effectiveness. The models are positioned as OpenAI's strongest cybersecurity offer…
OpenAI launched the GPT-5.6 model family, introducing three tiers—Sol, Terra, and Luna—across ChatGPT, Codex, and its API. Sol, the flagship model, is positioned for stronger agentic coding, knowledge work, and cybersecu…
Anthropic's new product Claude Tag, integrated into Slack, can autonomously perform knowledge work tasks such as debugging, code review, and data aggregation, leading the author to declare that AGI—defined as an AI syste…
The Ethereum Foundation is deploying swarms of AI agents to red-team its network infrastructure, uncovering vulnerabilities including a remotely triggered panic in libp2p's gossipsub. The AI agents, organized into specia…
Monaco developed Monacoder, a cloud-hosted agent-developer workspace platform built on Coder, to enable cost-effective parallel AI coding agents after abandoning a tmux-based approach. The platform addresses gaps in exis…
OpenAI launched GPT-5.6 on July 9th with three tiers—Sol, Terra, and Luna—priced at $5, $2.50, and $1 per million input tokens respectively, positioning the model as an operating layer for long-running work with improved…