The Decoder
AI coding agents still need human cleanup on nearly three out of four tasks in a real-world test
Alibaba's new coding-agent benchmark, Co-Design Bench, tests AI agents on real user requests that already tripped them up in practice.
Read at The Decoder ↗Related
AI auditors catch most agent misbehavior but flood reviewers with false alarms, new study finds The Decoder
Nine AI agents tried autonomous research on open questions from US national labs and none passed the experts' bar The Decoder
Ripple-65B Preview delivers strong agentic coding results as a fully Apache 2.0 open US model The Decoder
Japan🦙 ALPACA-FW #14｜AIツールを正本にしない――Adapterを薄く保つ理由 Zenn (AI)
JapanClaude Codeが「41分止まっています、止めてよいですか」と聞いてきた処理は、動画を描いている最中だった：記録の空白で止まったと決め Zenn (AI)
