Phase 0: Long-Horizon Autonomy · ~45 minutes · Python (stdlib · horizon-curve simulator)
The Shift from Chatbots to Long-Horizon Agents
In 2023 a chatbot answered a question in one turn.
Hiring signal: Can operate the shift from chatbots to long-horizon agents in production
Introduction
In 2026 a frontier model routinely runs minutes to hours on a single task. METR's Time Horizon 1.1 benchmark (January 2026) puts Claude Opus 4.6 at 14+ hours of expert work at 50% reliability. The horizon has been doubling roughly every seven months since GPT-2. Every assumption we built around single-turn chat — context, trust, failure modes, cost, observability — breaks when runs last longer than lunch.
Type: Learn Languages: Python (stdlib, horizon-curve simulator) Prerequisites: Phase 14 · 01 (The Agent Loop) Time: ~45 minutes
Objective
Learning objectives
Unlock the full lesson
You've read the first 2 sections. The rest of this lesson covers The Problem, The Concept, Build, Check Yourself, Key Terms & Next — plus a hands-on lab, quiz, and project artifact.
Create a free account to unlock Phase 0 and Phase 1 of every course — no credit card.
Browse all courses · View pricing · DeVenture Academy