» Tag
coding-agents
26 postsIf 30% of SWE-Bench Pro Tasks Are Broken, Add an Uncertainty Budget
OpenAI's SWE-Bench Pro audit found ~30% of tasks broken. Learn how to version task validity and report uncertainty intervals in benchmarks.
Coding Agent Skips VMs and Sandboxes With a TypeScript Linux Engine
RapidNative's coding agent skips VMs and sandboxes, using Lifo, a TypeScript OS engine, and pg-mem to run Linux-like tooling inside a single request.
Kimi K3 benchmark: Chinese AI is cheap at coding, not planning
Benchmark testing shows Chinese AI models are pricey planners but 19x cheaper coders than Western rivals, based on real pass/fail test runs.
CommitBrief — AI code reviews, right in your terminal
A provider-agnostic, local-first CLI that reviews your staged changes, a historic range, or a whole GitHub pull request. Zero telemetry, no server. Free and open source.
commitbrief.comGhostCommit: the image-based exploit AI code reviewers miss
GhostCommit hides malicious instructions inside PNG images to bypass AI code reviewers like Cursor Bugbot and CodeRabbit undetected.
Agent-Native Software Engineering: Why Specs Alone Aren't Enough
Coding agents fail less at writing code than at holding architectural context. A look at spec-driven development's limits and what comes next.
MiniMax M2.7: Open-Source AI That Optimized Its Own Training
MiniMax's open-source M2.7 model actively shaped its own training via memory writes and skill-building, gaining 30% efficiency and matching GPT-5.3-Codex on SWE-bench Pro.
Local Model Showdown Round 9: Qwen 3.6, Nemotron, Qwythos Coding Test
Five LLMs face off on a real coding task via llama.cpp on an RTX 5090 in Round 9 of the Local Model Showdown series.
Sophos Finds Coding Agents Trip the Same EDR Rules Built for Attackers
Sophos finds Claude Code, Cursor, and Codex trigger EDR rules built to catch attackers, exposing new risks in agentic coding workflows.
AI Coding Agents Are Absorbing the Leaves, Not the Whole Tree
SWE-bench and METR data track fast AI coding gains, but verification cost — not raw difficulty — still defines where agents stop.
Harness Engineering: Curating Context to Scale AI Coding Agents
Harness engineering keeps AI models fixed and optimizes context and tools instead, encoding nonfunctional requirements for reliable agent output.