WorkspaceSnapshots

heycusp.com

Partial result
https://heycusp.com/gallery
Created Oct 15, 05:04 AM · claude-haiku-5.5
Download best
Run stopped with a partial result

The best available replica is preserved. Verification is incomplete.

Runtime budget too low for another build pass. Reference verification remains blocked: desktop-initial: Live reference is unverified: Live reference entry: pixels failed; rendered frames differ across independent loads; Live reference phase section-4 did not finish within 240 seconds; Live reference coverage is incompl…

View run activity
Attempt 1succeeded
3h 44m·$2.826 model spend

Evaluate candidate 4:part-7

7m 9s
Files from this stage
evidence · behavior-evaluation-job-766-attempt-1-obs-10-4c14fa008e.jsonevidence · behavior-evaluation-job-766-attempt-1-obs-22-4077f642a1.jsonevidence · behavior-evaluation-job-766-attempt-1-obs-25-00b209e77e.jsonevidence · behavior-evaluation-job-766-attempt-1-obs-37-9a57bd6470.jsonevidence · dependencies-evaluation-job-766-attempt-1-obs-10-4c14fa008e.jsonevidence · dependencies-evaluation-job-766-attempt-1-obs-22-4077f642a1.jsonevidence · dependencies-evaluation-job-766-attempt-1-obs-25-00b209e77e.jsonevidence · dependencies-evaluation-job-766-attempt-1-obs-37-9a57bd6470.jsonevidence · diff-evaluation-job-766-attempt-1-obs-10-4c14fa008e.pngevidence · diff-evaluation-job-766-attempt-1-obs-22-4077f642a1.pngevidence · diff-evaluation-job-766-attempt-1-obs-25-00b209e77e.pngevidence · diff-evaluation-job-766-attempt-1-obs-37-9a57bd6470.pngevidence · graphics-evaluation-job-766-attempt-1-obs-22-4077f642a1-0-surface-eff0yu.pngevidence · graphics-evaluation-job-766-attempt-1-obs-22-4077f642a1-1-surface-eff0yu.pngevidence · graphics-evaluation-job-766-attempt-1-obs-22-4077f642a1-2-surface-eff0yu.pngevidence · graphics-evaluation-job-766-attempt-1-obs-22-4077f642a1-3-surface-eff0yu.pngevidence · graphics-evaluation-job-766-attempt-1-obs-22-4077f642a1-diff-0-surface-eff0yu.pngevidence · graphics-evaluation-job-766-attempt-1-obs-22-4077f642a1-diff-1-surface-eff0yu.pngevidence · graphics-evaluation-job-766-attempt-1-obs-22-4077f642a1-diff-2-surface-eff0yu.pngevidence · graphics-evaluation-job-766-attempt-1-obs-22-4077f642a1-diff-3-surface-eff0yu.pngevidence · graphics-evaluation-job-766-attempt-1-obs-25-00b209e77e-0-surface-eff0yu.pngevidence · graphics-evaluation-job-766-attempt-1-obs-25-00b209e77e-1-surface-eff0yu.pngevidence · graphics-evaluation-job-766-attempt-1-obs-25-00b209e77e-2-surface-eff0yu.pngevidence · graphics-evaluation-job-766-attempt-1-obs-25-00b209e77e-3-surface-eff0yu.pngevidence · round-evaluation-job-766-attempt-1-obs-10-4c14fa008e-agent.jpgevidence · round-evaluation-job-766-attempt-1-obs-10-4c14fa008e.pngevidence · round-evaluation-job-766-attempt-1-obs-22-4077f642a1-agent.jpgevidence · round-evaluation-job-766-attempt-1-obs-22-4077f642a1.pngevidence · round-evaluation-job-766-attempt-1-obs-25-00b209e77e-agent.jpgevidence · round-evaluation-job-766-attempt-1-obs-25-00b209e77e.pngevidence · round-evaluation-job-766-attempt-1-obs-37-9a57bd6470-agent.jpgevidence · round-evaluation-job-766-attempt-1-obs-37-9a57bd6470.pngevidence · timeline-evaluation-job-766-attempt-1-obs-22-4077f642a1.pngevidence · timeline-evaluation-job-766-attempt-1-obs-25-00b209e77e.png