According to Demis Hassabis, LLMs feel uncreative because they only perform pattern matching. To achieve true, extrapolative creativity like AlphaGo's famous 'Move 37,' models must be paired with a search component that actively explores new parts of the knowledge space beyond the training data.

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.

With models like Gemini 3, the key skill is shifting from crafting hyper-specific, constrained prompts to making ambitious, multi-faceted requests. Users trained on older models tend to pare down their asks, but the latest AIs are 'pent up with creative capability' and yield better results from bigger challenges.

Karpathy found AI coding agents struggle with genuinely novel projects like his NanoChat repository. Their training on common internet patterns causes them to misunderstand custom implementations and try to force standard, but incorrect, solutions. They are good for autocomplete and boilerplate but not for intellectually intense, frontier work.

The Codex tool is distinct from the "GPT-5 Codec" model it contains. The specialized model is tuned only for coding and performs poorly on other tasks. For document analysis, summarization, and strategic thinking, product managers should stick with the general-purpose GPT-5 model for best results.

Instead of giving an AI creative freedom, defining tight boundaries like word count, writing style, and even forbidden words forces the model to generate more specific, unique, and less generic content. A well-defined box produces a more creative result than an empty field.

Newer LLMs exhibit a more homogenized writing style than earlier versions like GPT-3. This is due to "style burn-in," where training on outputs from previous generations reinforces a specific, often less creative, tone. The model’s style becomes path-dependent, losing the raw variety of its original training data.

Sam Altman acknowledged that models are becoming "spiky," with capabilities improving unevenly. OpenAI intentionally prioritized making GPT-5.2 excel at reasoning and coding, which led to a degradation in its creative writing and prose. This highlights the trade-offs inherent in current model training.

Sam Altman admitted OpenAI intentionally neglected the model's writing style, which became unwieldy, to focus limited resources on enhancing its core intelligence and engineering capabilities. This reveals a strategy of prioritizing foundational model improvements over user-facing polish during development cycles.