New SMU preprint, Caper: approve a coding agent's shell commands by first running each…
This is a dev post classified by AGK Intelligence as AI dev tools (a tool drop), kept by the Dev Radar because it carries real work, not commentary.
New SMU preprint, Caper: approve a coding agent's shell commands by first running each in a network-off container and showing what happened, not judging the text. SABER: 6.7% of tasks ended in harm vs 14.8% to 21.2% for six other approval systems. https://www.chevyphillip.tech/blog/caper-consequence-aware-approval-coding-agents/
Posted by Chevy Phillip (3.9k followers) 3 h ago · 1 likes · 59 views · view the original post on X. Kept by the Dev Radar as AI dev tools.
More dev work like this
- “AI is now improving the systems that run AI.” Thanks to @Forbes for covering Together… — @togethercompute
- Hy4 beat DeepSeek at remaking the GTA VI trailer 🎬 — @aimlapi
- Stop rebuilding your LinkedIn writing prompts from scratch. — @DanKornas
- Google Research 开源了 Harness²，让 Agent 自己去改外面那层配置，跑一轮下来在 WorkBuddy-Bench 上最多涨了 11.5 分。 — @bkdgiffug
- The real test of AI coding is what happens when the next agent builds on it. — @wallstengine
- We got Unsloth quants for Qwen3.8-Flash-Next, again. — @ItsmeAjayKV
- INSANE. Axiom just announced the formalization of the ENTIRE 7,500-page Stacks Project,… — @choblin29
- Tencent Hy4 from @TencentHunyuan is now supported in OpenClaw. — @openclaw
Every post is read and classified by AGK Intelligence: what it is, which market it belongs to, and whether the link is a real tool. 31.3k posts from 5k X accounts over the last 21 days, 9.3k tools, 12 markets. New posts are collected several times an hour and the full ranking is recomputed every hour — last update 2026-11-04 18:20 UTC. Full method.