Full-text search across 67344 articles. Combine with topic and date filters; results sorted by relevance.
Developers can stop large language models from hallucinating nonexistent API calls by injecting local documentation or current SDK source into the context window rather than relying on the model's training data, accordin…
Engineering teams adopting individual coding agents see productivity gains of only 20-30%, not the 2-3x they expected, according to an engineer's guide published by LeadDev. The guide attributes the shortfall to agents c…
A developer compiled a set of 10 reusable AI prompts for ChatGPT and Claude aimed at common software engineering tasks, including debugging, refactoring, unit test generation, documentation, regex writing, SQL optimizati…
Mistral migrated 40,000 lines of Fortran 77 from a European energy operator's reservoir simulator to C++ using AI agents for documentation and implementation, according to a September 9th case study, with reservoir engin…
OpenScholar raised reported citation F1 from 31.1 to 39.5 against a standard retrieval baseline using the same GPT-4o model on 100 Scholar-CS questions, according to its February 2026 Nature paper, while answer rubric sc…
Expo's documentation team has adopted Answer Engine Optimization (AEO) practices to make its docs more accessible to AI coding agents, which now build a significant portion of React Native and Expo apps. A key change was…
A new report highlights that advanced AI debugging assistants are significantly improving software development efficiency, with top-tier tools resolving 41% of production bugs within 24 hours compared to 13% for human-on…
OpenBMB's MiniCPM5-2B GGUF quantization, tested hands-on with llama.cpp, shows degraded performance on complex tasks: the Q8_0 model invented a nonexistent column in a SQL debugging task and failed a multilingual transla…
A new analysis argues that many complaints about AI in test automation stem from user error rather than genuine tool limitations, citing the most dangerous pitfall as AI models silently rewriting assertions to make tests…
Developer siropkin released chrome-bridge, an open-source tool that lets any AI agent drive a user's real, logged-in Chrome browser via one unpacked extension and a zero-dependency Node CLI, requiring Chrome ≥ 117 and No…
A developer released a self-contained C++ testbed on GitHub that compresses RGB textures as a shared low-resolution latent texture plus a tiny MLP decoder, trained entirely with Evolution Strategies rather than backpropa…
Docker Captain and AI Engineer Yhary from Colombia built a Docker Sandbox Kit mixin that automatically starts an MLflow tracking server for Claude Code, enabling out-of-the-box experiment logging and model versioning. Th…
Google released Gemini 3.8 Flash on Wednesday, its fourth Flash model in 106 days, claiming it matches larger rivals' performance on some coding benchmarks at lower cost, but the flagship Gemini 3.5 Pro, promised by CEO …
Rohit Edathil released Dagic, a typed DAG language and async execution engine that lets LLM agents compose registered tools into a typed DAG instead of calling them one at a time, avoiding the need to sandbox arbitrary g…
Amazon Web Services announced that Australian teams can now access OpenAI's GPT-5.6 Sol, Terra, and Luna models through Amazon Bedrock with global cross-Region inference from the Asia Pacific (Sydney) and Asia Pacific (M…
Anthropic's documentation for Claude Fable 5.1 and Claude Mythos 5.1 details behavioral differences and prompting patterns, advising users to test all effort levels (low, medium, high, xhigh, max) because effort level na…
A developer explains harness engineering, a methodology for building reliable AI agent systems by designing deterministic guardrails around large language models. The approach, highlighted by an OpenAI experiment where t…
Meta released Muse Spark 1.3 on September 2, 2026, into Muse Code and the Meta Model API, claiming it uses ~20% fewer tool calls and ~25% fewer tokens than Muse Spark 1.2, while Artificial Analysis found it consumes abou…
A developer's hands-on comparison of Claude Sonnet 4.5, GPT-5, and DeepSeek V3.2 finds Sonnet 4.5 best for refactors and agent workflows, GPT-5 fastest at 0.9s p50 latency on 200K context, and DeepSeek cheapest at $0.27 …
A new report on machine learning systems warns that secrets such as API keys and credentials are often mishandled, exposing applications to security risks. The report emphasizes the need for environment isolation, where …