Full-text search across 68374 articles. Combine with topic and date filters; results sorted by relevance.
Two viral posts claiming unnamed Anthropic engineers achieved 1000x gains with 'graph engineering' have drawn 1.1 million views since late July, but the posts trace to a course-selling cluster and cite no primary sources…
Apple's Metal GPU glossary 'metalworking' targets developers familiar with CUDA but new to Apple Silicon, mapping every concept from GPU cores to MLX's architecture with CUDA equivalents and real kernel code. The hyperli…
Vejas, an integration platform with no builder UI where coding agents write flows in VejasScript, has two production customers collecting NIS2 supplier-compliance evidence across eight EU countries. The platform runs on …
Exo, a new open-source AI agent harness from the project exoharness, enables recursive self-improvement by allowing agents to modify their own code, prompts, memory, and tooling at runtime, with an immutable event log to…
Anthropic's engineering guidance distinguishes AI agents from workflows, arguing that true agentic systems require four components: a language model 'cashier,' a 'constitution' of system prompts, deterministic tools for …
Software engineer and blogger Dan H. argues that calling an LLM a colleague or teammate creates a dangerous excuse for shifting blame, noting that he is on pace to merge around 650 AI-assisted pull requests this year wit…
Assistant UI, an open-source library for building AI chat interfaces, is used in over 2,000 GitHub repositories and receives 1.4 million npm downloads monthly, according to founder and CTO Simon Farshid in an episode of …
A new self-study course, 'From Gradients to ChatGPT,' teaches participants to build a complete LLM stack from scalar autodiff to a working chat assistant, with all code running on an M-series MacBook without cloud GPUs. …
A new technical approach proposes using LLM agents to automate the migration of legacy C++ code to Rust, addressing memory safety issues by treating the process as a structured prompt engineering task. The workflow invol…
OpenAI launched Frontier, an enterprise platform for managing AI agents, on February 5, with HP, Oracle, State Farm, and Uber as early customers, but the launch comes amid revelations that an OpenAI research agent breach…
SemiAnalysis's AgentX benchmark shows NVIDIA's Vera Rubin NVL72 delivers up to 30x higher AI-factory throughput per megawatt than GB300 NVL72 for agentic-coding inference, while GB300 NVL72 extends its order-of-magnitude…
A developer reports that Cursor and Windsurf, two AI-powered IDEs, handle context overflow errors differently, with Windsurf's Flow mode offering better error recovery through a 'Reset Context' action, while Cursor often…
Matt Pocock introduced Sandcastle, an AI agent orchestration tool that uses Git worktrees to run multiple AI agents in parallel without version control conflicts. The tool, available on GitHub and installable via npm, re…
Neuroscience labs are drafting internal AI policies after a live demonstration of Anthropic's Claude Code at a scientific retreat in Barbados showed agentic AI tools can build working applications in minutes, outpacing s…
A developer has completed a Google Summer of Code 2026 project for the sbi library, replacing its string-based network configuration with typed configuration objects across all estimator families. The new API uses frozen…
Researchers at the University of California San Diego used AI to decode the DNA signature of the 'initiator,' a genetic switch that helps determine when human genes turn on, identifying it in roughly 60% of human genes a…
A developer argues that the current AI chat interface imposes a 'copy-paste tax' on users, who must manually move AI-generated text into documents, spreadsheets, and other tools. The post proposes a new model where AI ou…
A developer spent two months building Vestibule, an open-source Python framework for the boring layer of RAG ingestion, with four AI agents handling design, review, implementation, and code review through GitHub pull req…
GitHub reports that commits have doubled, Honeycomb's PR rate has roughly doubled, and Anthropic cites a 67% increase in code production, but production incidents are also rising as existing Developer Experience (DevEx) …
A test of 162 personas across roughly 2,500 prompts found that role-play prompts do not improve Claude's output compared to asking directly, according to data cited in a new analysis. Anthropic's own guidance now favors …