Stop Using OpenCode
A security researcher warns users to stop using OpenCode, the most popular open-source AI coding agent with 161k GitHub stars, citing severe security flaws and poor design. The tool, described as fundamentally a web-stac…
Full-text search across 66278 articles. Combine with topic and date filters; results sorted by relevance.
A security researcher warns users to stop using OpenCode, the most popular open-source AI coding agent with 161k GitHub stars, citing severe security flaws and poor design. The tool, described as fundamentally a web-stac…
AWS now provides a managed MCP path that can connect AI coding agents to AWS documentation, APIs, and existing IAM credentials, with the enforcement point remaining AWS IAM, not the model. A developer walks through a rea…
Domain-specific languages (DSLs) and abstractions enable reliable use of large language models (LLMs) by providing clear boundaries that guide code generation, according to a 14 July 2026 article by Martin Fowler. The ar…
Claire explains that a harness is code written around an AI agent to make it more effective at a specific job, and she walks through the custom Claude Agent SDK harness she built to automate Sentry bug triage at ChatPRD.…
A developer built DevMentor, an AI-powered platform with a Voice-to-Pull Request pipeline that automates the entire software engineering lifecycle. The system converts voice commands into structured tasks, generates code…
AI-assisted programming has advanced to the point of real-time, on-demand app generation, but software quality has not improved accordingly. The author argues that LLM-guided synthesis succeeded by solving specification …
Navdeep Singh, known as NeetCode, discussed his journey from Amazon and Google to building NeetCode.io, a coding interview preparation platform, on The Pragmatic Engineer podcast. He argued that LeetCode-style interviews…
Loomcycle, an open-source sidecar runtime for AI agents, has reached v1.0 under the Apache-2.0 license. The Go binary provides a hardened agent loop, MCP support on both sides, multi-replica high availability, and runs a…
A developer introduced Mechanically-Falsifiable Independent Control (MFIC), a discipline for enforced tests and runtime checks that prevent AI agents and human developers from being confidently and silently wrong. MFIC r…
A.I. is creating jobs rather than eliminating them, according to Nvidia CEO Jensen Huang, who said executives blaming layoffs on artificial intelligence are "lazy." The shift in discourse comes as a majority of Americans…
Gunnar Morling, a technologist at Confluent and Java Champion, discussed building high-performance Java applications in the data space, including his work on Hardwood, a zero-dependency Java parser for Apache Parquet dev…
GitHub announced a new GitHub App designed for agent-first workflows, joining a growing ecosystem of coding tools converging on a similar "conductor" form factor. The move validates Conductor, which pioneered the approac…
IBM has released two new multilingual embedding models under the Apache 2.0 license, built on ModernBERT: a compact 97M-parameter model and a full-size 311M-parameter model. Both support over 200 languages, handle contex…
Google released Antigravity, a VS Code fork featuring a Manager View for orchestrating up to five parallel AI agents and a built-in Chrome browser for visual front-end verification. The IDE uses Gemini 3.1 Pro and Flash …
The article discusses the author's defense of Contributor License Agreements (CLAs) and the Affero GPL (AGPL) in open source projects, arguing that CLAs serve an important role by requiring contributors to attest they ha…
A study of 26 popular open-source repositories found that projects building AI coding tools merge far more pull requests with far less human discussion than established projects, with openclaw merging about 2,700 pull re…
A developer built a per-message RAG "memory recall" hook for Claude Code that embeds past notes and conversations with BAAI's bge-m3 model and injects the closest matches into context before each reply, capped at 2,048 b…
Spawn, a ten-person game-creation-engine startup founded in 2024, shipped 77,000 substantial code changes in the last 30 days — about 108 per hour — using a fleet of permanent AI agents, and spent $3.1 million on Anthrop…
Oxide published guidance for running self-hosted AI agents on its Oxide Cloud Computer by provisioning a virtual machine for the agent's orchestrator, which then creates ephemeral virtual machines for each agent session,…
An engineering analysis lays out five control planes — Context, Containment, Validation, Rollout and Accountability — that CTOs and AI leaders should use to scale agentic software engineering safely, arguing that human j…