When prompted to build an MVP, Fable 5 interpreted "minimal" too literally, delivering a version that was overly narrow and not genuinely useful. This conservative execution makes it less suitable for agile development cycles where an ambitious, "good enough" V1 is required to get customer feedback.

Anthropic strategically focuses on "vision in" (AI understanding visual information) over "vision out" (image generation). This mimics a real developer who needs to interpret a user interface to fix it, but can delegate image creation to other tools or people. The core bet is that the primary bottleneck is reasoning, not media generation.

In building a UI analysis tool, Felix Lee found that Gemini Pro was superior to Anthropic's Opus model for accurately placing "hotspots" on specific UI elements in a screenshot. This highlights that for vision-based coding tasks, model choice is critical, as performance can vary significantly.

GPT-5.4 has a stark capability split: it generates production-ready, error-free code via its Codex CLI but produces "staggeringly bad and tasteless" UI designs. This forces a hybrid workflow where developers use other models like Claude for front-end design before switching to GPT-5.4 for reliable deployment.

Fable 5's extreme thoroughness, while powerful, makes it unsuitable for tasks like writing product specs. Its outputs are too dense and detailed, missing the bigger picture in a way that can delay shipping. Sometimes a "dumber," more pragmatic approach is more effective for product development.

Despite AI's ability to generate functional code, replicating the nuanced, subjective quality of a specific designer's "taste" remains extremely difficult. Felix Lee, after spending weeks attempting to codify his own taste into an AI model with little success, notes it's a significant unsolved challenge.

Widespread adoption of AI for complex tasks like "vibe coding" is limited not just by model intelligence, but by the user interface. Current paradigms like IDE plugins and chat windows are insufficient. Anthropic's team believes a new interface is needed to unlock the full potential of models like Sonnet 4.5 for production-level app building.

According to Dreamer's CEO, the biggest capability missing from LLMs is "taste." By default, AI-generated applications and UIs are generic and identifiable by the model that created them. It requires extensive human effort in prompt engineering and templating to create delightful, non-generic user experiences.

Despite models being technically multimodal, the user experience often falls short. Gemini's app, for example, requires users to manually switch between text and image modes. This clumsy UI breaks the illusion of a seamless, intelligent agent and reveals a disconnect between powerful backend capabilities and intuitive front-end design.