Fetching from the wire…
01
02
03
04
05
06
07
08
Public story · 2026-03-16 · source-backed
Passing tests once is easy; maintaining code for 8 months without regression is where current agents collapse. The most rigorous long-horizon evaluation published. 696K+ views. X/Twitter
Each link below shares sources, entities, or timing with this story.
Alibaba released Qwen / Shared entity: Alibaba / Shared topic / What happened next / Tension
Linked by a graph relationship (Alibaba released Qwen); both cover Alibaba; overlapping topics (code, coding, month).
Linked by a graph relationship (Alibaba released Qwen); both cover Alibaba; overlapping topics (agent, benchmark, coding).
Alibaba uses Claude / Shared entity: Agent / Shared topic / What happened next / Tension
Linked by a graph relationship (Alibaba uses Claude); both cover Agent; overlapping topics (agent, code, coding).
Alibaba uses Claude / Shared entity: Twitter / Same source domain / What happened next / Tension
Linked by a graph relationship (Alibaba uses Claude); both cover Twitter; reported by the same outlet (x.com).
Alibaba uses Claude / Shared entity: Twitter / Shared topic / What happened next
Linked by a graph relationship (Alibaba uses Claude); both cover Twitter; overlapping topics (code, coding, collapse).
Alibaba uses Claude / Shared entity: Twitter / Same source domain / What happened next
Linked by a graph relationship (Alibaba uses Claude); both cover Twitter; reported by the same outlet (x.com).
Alibaba released Qwen / Shared entity: Alibaba / Shared topic / Earlier coverage
Linked by a graph relationship (Alibaba released Qwen); both cover Alibaba; overlapping topics (alibaba, code).
Alibaba released Qwen / Shared entity: Alibaba / What happened next / Tension
Linked by a graph relationship (Alibaba released Qwen); both cover Alibaba; picks up the Alibaba thread on 2026-06-28.