Overly structured, workflow-based systems that work with today's models will become bottlenecks tomorrow. Engineers must be prepared to shed abstractions and rebuild simpler, more general systems to capture the gains from exponentially improving models.

Performance gains increasingly come from the "harness"—the surrounding system of tools, data connections, and agentic workflows—not the underlying model. Stanford's "meta-harness" concept shows a 6x performance gap on the same model, suggesting the product layer is where real innovation and competitive advantage now lie.

The relationship between an AI model and its surrounding software "harness" is a delicate dance. Developers build complex harnesses to compensate for a model's weaknesses. However, as new, more capable models are released, developers must be willing to delete parts of that harness, which now become restrictive and hold the system back.

Overly prescriptive fixes or guardrails for current AI weaknesses are temporary. As models improve, this "scaffolding" becomes obsolete. Teams must stay flexible and be ready to remove old constraints with each new model release, rather than over-engineering for today's problems.

Features built to guide AI agents, like an explicit "plan mode," will become obsolete as models become more capable. The Claude Code team embraces this, building what's needed for the best current experience and fully expecting to delete that code when a new model renders it unnecessary.

The "bitter lesson" of AI applies to product development: complex scaffolding built around model limitations (like early vector stores or agent frameworks) will inevitably become obsolete as the models themselves get smarter and absorb those functions. Don't over-engineer solutions that a future model will solve natively.

Building on AI involves a "tick-tock" cycle. First, engineers create a complex "harness" of prompts and skills. Then, a new, more powerful base model is released that performs those skills natively, "eating the harness" and forcing engineers to simplify and build a new layer of more advanced heuristics.

Building on AI requires creating custom infrastructure to fill performance gaps. As underlying models improve, founders must be prepared to delete this now-redundant code and upgrade their product vision to tackle the next set of challenges at the new frontier. This cycle of building and deleting is key to staying innovative.

Many early AI product features, like Claude Code's initial "to-do list," are crutches built to compensate for model weaknesses. As underlying models become more capable, they perform these functions naturally, allowing teams to remove the crutch features and simplify the product.