Harness Engineering – first thoughts
Thoughtworks Distinguished Engineer Birgitta Böckeler reflects on an OpenAI article about using AI agents to build a massive codebase without…
Thoughtworks Distinguished Engineer Birgitta Böckeler reflects on an OpenAI article about using AI agents to build a massive codebase without…
Mitchell Hashimoto details his gradual, pragmatic journey toward effectively integrating AI into his software engineering workflow. He describes moving through…
Vivek Trivedy defines a “harness” as the crucial infrastructure surrounding an AI model that transforms it into a functional, autonomous…
Anthropic researcher Prithvi Rajasekaran explores how to improve AI agents’ performance in tasks involving subjective design and complex, autonomous software…
Anthropic engineers address the challenge of getting AI agents to accomplish complex software tasks that exceed a single context window.…
An experiment where a team built and shipped a complex software product entirely through AI agents, with zero lines of…
Capital One will present eight research papers at ICML 2026 in Seoul focused on large language model safety and reasoning.…
A comprehensive review from Zylos Research finds that AI safety has matured from theoretical research to practical deployment in 2026,…
The Council on Foreign Relations argues that artificial intelligence is entering a decisive phase defined less by speculative breakthroughs than…
Stanford Human-Centered AI Institute researchers predict that 2026 will mark a turning point from AI speculation to careful measurement of…
Microsoft introduced Microsoft Frontier Company on July 2, 2026, committing $2.5 billion to embed 6,000 industry and engineering experts directly…
AWS announced a $1 billion investment on July 2, 2026 in forward-deployed engineering, placing thousands of AI engineers directly within…