Full-text search across 67015 articles. Combine with topic and date filters; results sorted by relevance.
Cline migrated its VS Code extension, used by over 11 million developers, to the new Cline SDK, a move that reduced agent failures by 10x after an initial failed attempt forced a safer rollout strategy. The company rebui…
An analysis of OpenAI's open-source Codex repository shows a step change in development velocity, with commits per month rising from 98 in May 2025 to 893 in August 2026, and authors with 5+ commits growing from 2 to 35.…
Anthropic launched Claude Fable 5.1 and Claude Mythos 5.1 as its new flagship models for coding and knowledge work, claiming they are the world's most advanced for these tasks. The models keep list pricing at $10/$50/$12…
A developer built a failure classifier to distinguish between client-side bugs, model/API issues, and server infrastructure problems after a 48-hour experiment on a free model endpoint. The classifier, which sorts failur…
Google could release Gemini 3.8 Flash as soon as September 2, according to The Wall Street Journal, with employees reporting that the model, internally named 'Skimaki,' has significantly improved coding abilities and was…
McKinsey's 2026 State of AI survey, released August 25, 2026, found that 32% of 1,719 respondents across 97 countries skipped buying at least one software product or feature because they could build it internally with ag…
Figma's security engineering team built an AI agent on AWS Bedrock Knowledge Bases and Amazon Kendra that triages alerts, conducts forensic investigations, queries the security data lake, writes code fixes, and remembers…
Conductor, a Mac app that runs Claude Code, Codex, and Cursor agents in parallel isolated workspaces, offers a free tier for local use, Pro at $50 per month, Teams at $60 per user per month, and custom Enterprise pricing…
Google Stitch, a free AI interface design tool from Google Labs, turns prompts, sketches, or voice input into multi-screen UI designs on an infinite canvas and exports front-end code in multiple frameworks. Announced at …
Cisco Talos has published a structured workflow for safely analyzing obfuscated JavaScript in phishing kits and malicious npm packages. The method preserves the original file, restores strings, identifies execution sinks…
Z.ai revealed that the mystery model Ox-Alpha on OpenRouter and OpenCode was its GLM-5.3-Flash, a 320B-parameter multimodal MoE model with 18B active parameters, and released its weights on Hugging Face the same day. The…
A developer introduces the emerging discipline of harness engineering, which focuses on designing the environment, tools, and feedback loops around AI coding agents to ensure they reliably produce software. The approach …
Datology released DataSmith, an autonomous data research harness that improves base models by iteratively changing only training data, and introduced CurateBench, a benchmark for data curation research. On CurateBench, L…
AI-assisted agentic coding has reached escape velocity, but non-programming use cases lag due to a lack of version control, according to an analysis. The author argues that without version control, using AI for tasks lik…
Microsoft's Copilot strategy is facing adoption challenges due to fragmented launches, pricing changes, and technical pivots, according to a developer's analysis. The developer contrasts Microsoft's approach with OpenAI'…
DeepSeek AI released DeepSeek-V4-Pro-0813, the official non-preview version of its open-weight coding and agentic model, reporting gains over the preview on every listed benchmark. On Terminal Bench 2.1 it scores 87.9, b…
One in five AI/ML 510(k) clearances cites a predicate under a different product code, with 85 devices predicated on a different body region, 35 swapping imaging modality, and 122 crossing 21 CFR regulation numbers, accor…
As of mid-2026, most software developers have stopped writing functions manually, with AI generating the majority of code, according to a developer reflecting on the industry shift. The author argues that without oversig…
GitHub has launched the session catalog for GitHub Universe 2026, a two-day event featuring sessions from AMD, Figma, NVIDIA, Coinbase, Anthropic, and OpenAI, with early bird registration saving $300 before August 19. Th…
An engineer's guide outlines five verification checks to confirm an AI agent actually completed its work, emphasizing that a report is not evidence and only the state of the delivered artifact proves completion. The guid…