Claude Code will default to auto mode despite an 11% test miss rate
Anthropic is making Claude Code auto mode the default August 14 after tests showed it beat manual review while still missing some dangerous commands.
Tag
#Developer Tools
9 articles
TECHi reporting and analysis covering Developer Tools. 9 articles, newest first.
Harness Agent DLC Puts AI Releases Under One Change Record
Harness Agent DLC links evals, prompts, deployments, assets and traces. TECHi tests what is live, what is roadmap, and whether release history survives.
llama.cpp b10075 Packs Four Local AI Runtime Upgrades
llama.cpp b10075 connects browser agents, conversation controls, leaner DSV4 state saves, and Qualcomm Hexagon support in one local AI runtime update.
Claude Code 2.1.216 Tests Whether Agent Permissions Survive the Handoff
Claude Code 2.1.216 targets permission drift across resumed agents, isolated worktrees, rewind, and sandbox controls. Here is what teams should test.
Cline CLI 3.0.45 cuts install footprint by unbundling AI providers
Cline CLI 3.0.45 cuts its resolved install tree by 55% by moving Claude Code and Codex runtimes out of the default path and tightening agent roles.
Replit’s AI Agents Nearly Tripled Output. Now Comes the Road Test
Replit says AI agents lifted same-cohort code output 2.9x. Its architecture looks credible, but the productivity case still needs a controlled cost test.
CrewAI 1.15.3 Puts Control Hooks Inside AI Agent Runs
CrewAI 1.15.3 adds interception hooks, opt-in tool caching, and per-call usage data, giving teams finer control over production AI agent runs and costs.
JAX 0.11.0 Makes AI Training Memory Policy Programmable
JAX 0.11.0 adds programmable rematerialization for AI training, while a higher dependency floor and changed empty-array behavior raise upgrade risk for teams.
Grok Build turns xAI into an AI coding-agent contender
xAI's Grok Build brings terminal coding agents, headless automation, plugins, MCP and enterprise controls into the race with Codex and Claude Code.