Fetching from the wire…
01
02
03
04
05
06
07
08
Research2026-08-11 · source-backed
The Replay Gap (arXiv 2608.08239) forked live SWE-bench trajectories at controlled points, rebuilt the environment, and continued each fork with a different model across ~900 rollouts. Model swaps rewrote 61–94% of post-fork actions and diverged at the very first post-fork action 74–77% of the time, versus 6–35% for same-model controls. All five outcome flips occurred in swap arms, zero across 359 control forks. A log-stitching replay evaluator mispredicted every success-relevant outcome and produced patches with 0.00–0.11 similarity to reality. If you route per-step between Haiku and Opus, branch live or don't trust the number.
Each link below shares sources, entities, or timing with this story.
Opus built by Anthropic / Shared entities / Shared topic / Earlier coverage
Linked by a graph relationship (Opus built by Anthropic); both cover Haiku, Model, Opus; overlapping topics (agent, model).
Claude Code uses Opus / Shared entities / Same source domain / Shared topic / Earlier coverage
Linked by a graph relationship (Claude Code uses Opus); both cover Model, Opus; reported by the same outlet (arxiv.org).
Claude Code uses Opus / Shared entities / Shared topic / Earlier coverage / Tension
Linked by a graph relationship (Claude Code uses Opus); both cover Haiku, Opus; overlapping topics (agent, between).
Claude Code uses Opus / Shared entities / Shared topic / Earlier coverage
Linked by a graph relationship (Claude Code uses Opus); both cover Haiku, Opus; overlapping topics (action, different, model).
Cursor uses Opus / Shared entity: Haiku / Same source domain / Shared topic / Earlier coverage / Tension
Linked by a graph relationship (Cursor uses Opus); both cover Haiku; reported by the same outlet (arxiv.org).
Claude Code uses Opus / Shared entities / Shared topic / Earlier coverage
Linked by a graph relationship (Claude Code uses Opus); both cover Opus, SWE; overlapping topics (agent, model).
Claude Code uses Opus / Shared entities / Same source domain / Earlier coverage
Linked by a graph relationship (Claude Code uses Opus); both cover Opus, SWE; reported by the same outlet (arxiv.org).
Linked by a graph relationship (Claude Code uses Opus); both cover Opus, SWE; reported by the same outlet (arxiv.org).