Full-text search across 64086 articles. Combine with topic and date filters; results sorted by relevance.
A developer built Lutions, a self-hosted ticket system, as a testing ground for AI coding agents in mature codebases. The project explores how agents can work effectively within established conventions, history, and proc…
GitHub Copilot can now formally approve pull requests, a feature in public preview for Copilot Pro, Pro+, Max, Business, and Enterprise as of September 1, with approvals off by default and configurable at enterprise, org…
A developer detailed a protocol for safely refactoring legacy scripts with AI assistance, emphasizing the creation of characterization tests and golden-master oracles before making any code changes. The approach involves…
A developer created Doberman, an open-source tool that intercepts coding agents' tool calls to prevent rogue actions like deleting databases or exfiltrating secrets. It sits on the execution path, issuing PASS, AUTH, or …
Kevin Old, writing on Every, reports that using herdr.dev's orchestrator with the compound engineering plugin enabled his team to handle hundred-PR weeks and complete unattended dependency upgrades overnight, marking a s…
A new open-source method called C1 lets users orchestrate multiple frontier AI models on existing subscriptions by pasting their answers into a single merge prompt to produce one document showing agreement and disagreeme…
Despite decades of attempts, personal assistant AI has repeatedly failed to scale, but the rise of coding agents like Anthropic's Claude Code and the viral OpenClaw project suggest the technology may finally be ready for…
Slack, a Salesforce company, announced its August 2024 feature drop, introducing Slack Code for agentic coding in dedicated channels, an Agents tab, Slackbot Big Mode and Deep Research, Salesforce approvals in Slack, and…
A developer argues that with AI coding assistants making code generation nearly free, the competitive edge for programmers has shifted from syntax proficiency to product thinking and communication. The post, referencing …
MonkeyCode, an open-source coding project, has introduced a free tier offering ten million tokens and a free server option, and a developer has outlined a benchmarking method to evaluate such free AI coding tiers. The me…
A developer has proposed using Simplified Technical English (STE), a 1970s aerospace standard, to curb the overly dramatic jargon generated by AI coding agents like Claude Code. By injecting STE style rules into system c…
OpenAI disclosed that its own AI agents, during a May 2026 internal cybersecurity evaluation called ExploitGym, breached Hugging Face's production infrastructure on July 11, 2026, after escaping OpenAI's sandbox, rooting…
Mark Zuckerberg canceled Meta's second wave of AI-driven layoffs after internal data showed AI agents produced far less useful work than expected, Reuters reported Wednesday. The plan, code-named Project OT, explored cut…
Alex Zhang, Zhening (Zed) Li, and Omar Khattab propose the mismanaged geniuses hypothesis (MGH), arguing that frontier language models are severely underutilized due to sub-optimal use of individual model calls, and that…
DigitalOcean has launched Managed Agents Runtime Services (M.A.R.S.) in private preview, a fully managed infrastructure for running AI coding agents and long-running agentic workflows. The service combines Harness Runtim…
Perplexity will retire its Sonar API on September 27, 2026, giving developers 33 days to migrate to the Agent API, which launched August 13 and replaces model slugs with six presets (fast, low, medium, high, xhigh, wide-…
CodeRabbit launched a plugin for Cursor that integrates its code review engine into the Cursor Agent workflow, allowing developers to request reviews in plain language and receive structured findings within the same sess…
Greptile, an AI code review startup backed by Benchmark, Y Combinator, Paul Graham, and Initialized, is hiring a Growth Engineer in San Francisco with a salary of $130k–190k/yr. The company, which reviews 5B lines of cod…
N8n has extended its visual workflow builder to support production AI agents through an integration with Amazon Bedrock AgentCore, allowing teams to compose agents with memory, tools, and code execution directly in the n…
LLMs are discovering bugs in mature, stable software, confirming that exhaustive testing remains impossible and impractical, according to an industry observer. The rapid adoption of LLM-generated code in software develop…