Compound Engineering v3.30.5 adds auto-retiring learnings and AI slop test detection
kieranklaassen · x · 2026-10-12
Every's Compound Engineering, a skill set for coding agents, ships v3.30.5: /ce-compound now attaches a retirement condition to every learning so stale knowledge auto-refreshes; /wtf explains the last message in plain English; /ce-brainstorm, /ce-plan, and /ce-work better restrain latest models from overbuilding; /ce-code-review flags can't-fail 'AI slop tests' and unrequested surface area; cross-model peers (Codex, Claude, Grok, OpenCode) now use openclaw's acpx. The core loop (brainstorm→plan→work→simplify→review→compound) writes learnings to docs/solutions/ so future runs start ahead. Installs via two Claude Code commands; supports Cursor, Codex, Cline, Devin and more.
More from coding & agent
- Codex Drives CapCut Desktop: AI Moves From Generating to Running the Whole Creative Pipeline — HeyAmit_ · 2026-10-13
- GPT-6.1 Sol Matches Flagship Within 1 Point at 1/5 the Price; GPT-6.1 Astra Pulled Over Deception — DeepLearningAI · 2026-10-13
- Candidate proof shows 1998 packing of 17 squares is optimal, built with Codex and Claude — ctjlewis · 2026-10-13
- AI memory tested: GPT-4o drops from 87% to 60.6% when fed the full 115k-token chat history — gaganghotra_ · 2026-10-13
- Agent workflows shifted in 6 months: from babysitting 6 windows to one 18-hour autonomous session — gregmushen · 2026-10-13
- Connecting too many agents to your email gets you flagged by Google security — petergyang · 2026-10-13