Lower Yosemite Falls (May 2026)
Yosemite Valley (May 2026)
Marin Headlands (Apr 2026)
Palace of Fine Arts (Oct 2025)
Marin Headlands (Jul 2025)
Mallorca Cap de Formentor (Jul 2025)
Marina District (May 2025)
Outskirts of Seattle (Mar 2025)
Chestnut Street (Feb 2025)
Golden Gate (Jan 2025)
Ocean Beach (Feb 2022)
Tank Hill (Jun 2020)
Big Sur (Dec 2016)
Lower Yosemite Falls (May 2026)
Yosemite Valley (May 2026)
Marin Headlands (Apr 2026)
Palace of Fine Arts (Oct 2025)
Marin Headlands (Jul 2025)
Mallorca Cap de Formentor (Jul 2025)
Marina District (May 2025)
Outskirts of Seattle (Mar 2025)
Chestnut Street (Feb 2025)
Golden Gate (Jan 2025)
Ocean Beach (Feb 2022)
Tank Hill (Jun 2020)
Big Sur (Dec 2016)
Lower Yosemite Falls (May 2026)
Yosemite Valley (May 2026)
Marin Headlands (Apr 2026)
Palace of Fine Arts (Oct 2025)
Marin Headlands (Jul 2025)
Mallorca Cap de Formentor (Jul 2025)
Marina District (May 2025)
Outskirts of Seattle (Mar 2025)
Chestnut Street (Feb 2025)
Golden Gate (Jan 2025)
Ocean Beach (Feb 2022)
Tank Hill (Jun 2020)
Big Sur (Dec 2016)
A benchmark for long-horizon software building: seventeen full-stack apps, 241 feature requests, and 544 test plans, showing that even top models only ship fully working products 49–65% of the time.
Why letting frontier models choose their own effort level, handoffs, and subagents beats prescriptive routing — the bitter lesson of harness design, applied to Replit Agent.
How evaluation at Replit went from launch check to improvement loop — learning from production traces to ship a better Replit Agent, week over week.
I spent a couple of years building email and voice agents for freight carrier sales. Three takeaways stuck with me.
