Practical AI · Thursday, July 9, 2026
Hamza Tahir describes how AI "harnesses" or frameworks, like Claude Code, become deeply coupled with the specific large language models they are designed for. This coupling, driven by reinforcement learning and specialized tool use, means that models become 'self-aware' of the harness they are running within, leading to more accurate performance.
“So what they did was they, uh, like Claude Code for instance, the harness is, is Claude Code, and underlying it is Opus 2.5.”
“And, uh, Opus 2.5 by now, unlike Opus 3.5, understands what Claude Code itself is. So it's self-aware in the way it's running inside Claude Code.”
“The harness, uh, with the reinforcement learning loop that has gone on for the last year and a half. Uh, has coupled deeply with the model.”