Full-text search across 66357 articles. Combine with topic and date filters; results sorted by relevance.
Medusa has built agentic automations, using Claude Code, to handle its release workflow, including drafting release notes, updating documentation, and generating changelog entries, according to a September 17, 2026 compa…
TypeScript 6.0 introduces the --strictBuiltinIteratorReturn flag, which changes the BuiltinIteratorReturn type parameter from any to undefined for built-in iterators, closing a type hole that existed since TypeScript 2.3…
Nxm-memory, a local memory and search engine for AI assistants, indexes an entire workspace on the user's own machine and exposes its tools through the Model Context Protocol (MCP) to cut the number of tokens sent to a m…
Bluebox, a tool that lets developers and coding agents query live production telemetry, demonstrated its ability to diagnose a production incident where adding a last_activity_at timestamp to an account record caused p99…
Checkly, a monitoring platform, rewrote its Results Daemon service from Node.js to Go using Claude Code, an AI agent, and shipped it with zero incidents despite processing approximately 92 million messages daily. The rew…
Databricks explains that an AI copilot is an in-app assistant using large language models and workflow context to provide real-time suggestions, generated content, or automated actions, with the human remaining in contro…
A2acast, a new open-source tool by developer husker, enables AI agents on different computers to communicate directly without a central server, accounts, or open ports, using a single stdlib-only Python file and end-to-e…
A developer building an autonomous Claude Code environment discovered that the Stop hook payload lacks a usage field, causing a cost-tracking script to silently record zero token counts for 52 days and 2,340 rows. The fi…
Developer kelviq released Tare, an open-source tool that lets Claude Code users query its own logs in plain English to diagnose why their usage quota is draining, after the creator's own Claude quota ran out in 10 minute…
A developer who used AI to build a web service discovered that the LLM-generated code included sophisticated CSRF protection, complete with macros and detailed comments. The AI refactored the middleware to use functional…
A hands-on comparison of eight ChatGPT alternatives found Anthropic's Claude the closest replacement, with Mistral's Le Chat offering the best value at $14.99/month, according to a tester who spent weeks evaluating long-…
A developer argues that programmers who get the best results from AI treat it as a junior engineer and use spec-driven development combined with Socratic inquiry, rather than pasting vague prompts. The workflow involves …
Google's blog post argues that Go is ideal for AI-assisted software engineering because its compiler provides a deterministic feedback loop for code verification, shifting the bottleneck from writability to verification.…
AMD has surpassed its AI productivity target, achieving a 30 percent overall productivity boost in software development within a year, up from the 25 percent goal set for two to three years. The company reports that AI-g…
Dupflo released Decision Ledger, an experimental set of three agent skills for Claude Code that records developers' architectural decisions and tracks how many they could defend in review, with the tool itself publicly s…
Neciu Dan, technical co-founder of an ed-tech startup and Staff Software Engineer, published a guide on AI agent architecture, explaining that an AI agent is a model choosing steps inside a loop your code runs, enabled b…
Evil Martians, a software development agency, published a how-to guide for shipping AI agent skills as packages, reporting that coding agents read its site more than twice as often as humans over two months (268,000 agen…
A researcher investigating whether fine-tuning breaks a transformer's induction head circuit found that a bug in the induction score measurement initially caused the known induction head L1H6 in the attn-only-2l model to…
Black Hat USA 2026 Arsenal will feature 101 open-source security tools, including new AI-focused offerings such as AgentsLeak, a runtime protection platform for AI coding agents, and ARAY, which generates benign binaries…
The Rust compiler team published an LLM policy for its rust-lang/rust monorepo stating that LLMs may answer, analyze, and review code but not create it, requiring tests for LLM-written pull requests and banning soundness…