The model performs impressively on one-shot, greenfield projects but struggles with the critical final details and edge cases. When pushed to refine or iterate on a task, it begins to introduce bugs and loses consistency, revealing a significant weakness in handling sustained complexity.

When choosing between Opus 4.6 and Codex 5.3, consider their failure modes. Opus can get stuck in "analysis paralysis" with ambiguous prompts, hesitating to execute. Conversely, Codex can be overconfident, quickly locking onto a flawed approach, though it can be steered back on course.

A key new feature in the Opus 4.6 API is "Adaptive Thinking," which lets developers specify the level of effort the model applies to a task. Setting the effort to 'max' forces the model to think without constraints on depth, a powerful but resource-intensive option exclusive to the new version.

Beyond standard benchmarks, Anthropic fine-tunes its models based on their "eagerness." An AI can be "too eager," over-delivering and making unwanted changes, or "too lazy," requiring constant prodding. Finding the right balance is a critical, non-obvious aspect of creating a useful and steerable AI assistant.

For advanced AI models, providing a high-level goal rather than a detailed, prescriptive list of instructions often produces better outcomes. Over-prompting can constrain the model's intelligence, while a simpler prompt allows it to leverage its own planning capabilities for a more effective execution.

The traditional lever of `temperature` for controlling model creativity has been superseded in modern reasoning models, where it's often fixed. The new critical parameter is the "thinking budget"—the amount of reasoning tokens a model can use before responding. A larger budget allows for more internal review and higher-quality outputs.

Unlike previous models that benefited from iterative guidance, Anthropic's team suggests Opus 4.7 delivers higher quality results when treated like a capable engineer. Users should provide the full goal and constraints upfront, as multi-turn clarification can actually reduce output quality.

Like human experts, advanced AI models improve their answers the more time they spend on a problem. This 'inference scaling' means short evaluations may fail to capture a model's true capabilities, as performance continues to increase with more computation, making it difficult to establish a performance ceiling.

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.