Full-text search across 61633 articles. Combine with topic and date filters; results sorted by relevance.
A statistical analysis of 5,009 git repositories and 10,812 developers from 2019 to mid-2026 found that AI-tool mentions in commit messages rose from near zero to 1 in 8 commits by July 2026, and a separate signal—a sudd…
METR, an AI safety and capability research organization, conducted a randomized controlled trial in 2025 with 16 experienced open-source developers working on 246 real-world tasks. The study found that developers using A…
Cornell University developers built custom AI Skills for security and accessibility audits, using parallel sub-agents to scan entire codebases for vulnerabilities and compliance issues. The security audit, developed with…
A security scan of the open-source URL shortener iShortn by ZeroQuarry found 13 high-severity and 33 medium-severity issues, including authorization flaws and multiple server-side request forgery paths, all of which have…
Google's Gemini 1.5 Pro and Flash models can expose API keys and leak sensitive data if not properly secured, according to a developer's guide that recommends using .env files, strict system instructions, and regex-based…
DeepSeek released DeepSeek V4.1 Flash 1017 on 17 October 2026, a 763B-parameter open-weights update to V4.1 Flash published under the MIT License, with a 1M-token context window and 384K-token maximum API output. DeepSee…
A University of Washington study of 1.16 million Jupyter notebooks from 264,000 GitHub repositories found that only 24% of 863,878 executed without errors and only 4% produced identical results on a second run, highlight…
NVIDIA released Nemotron 3 Super, a 120-billion-parameter hybrid model that scores 60.47% on SWE-Bench Verified, beating GPT-OSS-120B by nearly 20 points while delivering 2.2 times the inference throughput. The model com…
Anthropic released Claude Opus 5.5, the first model in the Claude 5.5 family, and CodeRabbit's evaluation found both of its tested configurations caught slightly more open-source bugs than the production baseline while p…
An unidentified multimodal AI model called Union Alpha surfaced unannounced on model-routing platforms including OpenRouter with a 262K token context window and no lab claiming it. On a software engineering benchmark sha…
A developer integrated DeepSeek's API into a TypeScript pipeline using the OpenAI SDK, finding that the API's compatibility makes integration trivial but that model evaluation depends on specific use cases. The developer…
GitHub Distinguished Engineer Stephen Toub migrated the GitHub Copilot agent runtime from TypeScript to 832,378 lines of production Rust across 128 pull requests between 12 May and 21 August 2026, at a cost of about $120…
OpenCode 2.0 and Codex CLI 0.157.0 both now start a resident background server by default, with OpenCode's service listening on localhost port 49374 (45278 on Windows) and Codex's daemon auto-updating hourly, according t…
An analysis of 1,674 agent sessions across RocketSim, RocketTrace and other Swift apps found that 94.2% of all tokens were cache reads while the agent's own replies accounted for just 0.6%, according to the developer's o…
A developer ran 32 controlled generations across four open-weight models (DeepSeek v4 Pro, Llama 4 Maverick, GLM 5.3, Mistral 3 14B) using the same prompt but swapping in two different commits of their own football quiz …
A developer published a step-by-step guide for deploying Google's 2B Gemma 4 model to Cloud Run with an NVIDIA L4 GPU, using vLLM for serving and a single-file Python MCP server to stage weights, deploy, health-check, be…
A developer team at an unnamed company built an ephemeral environment on AWS to improve pull request review workflows, triggered by GitHub Actions, which builds a Docker image, pushes it to Amazon ECR, and updates a prev…
Zhipu AI's GLM 5.3 large language model scored 28.3 on terminal-bench 3, up from GLM 5.2's 4.6, without changing base weights, according to a hands-on review. In live tests, GLM 5.3 added a real-time viewer counter to a …
An AI model reviewed CodeMeridian's "Human Cognitive Seed" feature, which presents developers with multiple candidate implementations to evaluate rather than a single AI-generated answer. The model praised the approach f…
Anthropic's Claude Opus 5.1 model is being used by developers to generate playable browser games and 3D scenes in a single prompt, including a class-based FPS shooter by Riley Brown, a Mario Kart clone by Bridgemind, and…