The importance of speed in AI is deeply psychological. Similar to consumer packaged goods where faster-acting ingredients create higher margins and brand affinity, low-latency AI creates a powerful dopamine cycle. This visceral response builds brand loyalty that slower competitors cannot replicate.

As frontier AI models reach a plateau of perceived intelligence, the key differentiator is shifting to user experience. Low-latency, reliable performance is becoming more critical than marginal gains on benchmarks, making speed the next major competitive vector for AI products like ChatGPT.

The speed of models like SWE 1.7 is more than a convenience; it fundamentally changes user behavior. It eliminates the awkward latency gap where tasks are too slow for real-time interaction but too fast to fully context-switch. This enables a new "watch it work" workflow, keeping users in a state of flow.

Companies like OpenAI and Anthropic are intentionally shrinking their flagship models (e.g., GPT-4.0 is smaller than GPT-4). The biggest constraint isn't creating more powerful models, but serving them at a speed users will tolerate. Slow models kill adoption, regardless of their intelligence.

Frame the value of speed beyond just a better user experience. Ask customers how they could use the time saved by faster AI responses to pack in more value, create premium product tiers, or open entirely new revenue streams that were previously impossible.

While Linear typically prioritizes quality over speed, Karri Saarinen acknowledges that in rapidly changing markets like AI, speed is more critical. Because the problems and workflows are unknown, shipping faster is necessary to get market feedback, find problems, and identify opportunities before the landscape solidifies.

Model speed is not just a cost metric; it's a powerful user experience driver. Once users become accustomed to a fast, responsive model, it becomes very difficult for them to tolerate slower ones, creating a sticky product advantage similar to the adoption of high-speed internet.

Speed is crucial for all AI applications, not just interactive ones. For background "agentic" tasks, a faster system provides a compounding business advantage. If a competitor's AI can complete ten tasks while yours does one, that lead grows exponentially over time.

When technical performance hits a ceiling, design can solve the user's experience of speed. Perceived performance is a design problem addressed through interactions, optimistic UI, and loading states, making the product feel faster even when the underlying systems are not.