{"slug": "i-tested-every-al-model-the-same-way-only-one-task-got-better", "title": "I tested every Al model the same way. Only one task got better", "summary": "Adlet Balzhanov, a software developer, reports that after testing every AI model with the same coding and writing tasks, only coding improved, while writing outputs remained generic and AI-sounding regardless of model strength or prompt tweaking. He concludes that AI excels at tasks with checkable outputs like software, but for writing, the best approach is not to use AI at all.", "body_md": "# I tested every AI model the same way. Only one task got better\n\nI’ve been testing every new AI model the same way for a while now. I give it a real coding task, and more often than not it comes back with something solid, impressive results. Then I give it a pile of good writing samples and ask it to write an article or a design doc in that voice, and it fails. Doesn’t matter how strong, expensive the model is or how many examples I feed it. It always comes back sounding like AI.\n\nFor a while I assumed it was on me. Bad prompting, not enough samples or wrong instructions. So I kept tweaking it for a while, and it never got better in any way that mattered.\n\nSoftware or code has a right, finite answer. It compiles or it doesn’t, the tests pass or they fail. And the model has something concrete to aim at and correct itself against. The best practices and patterns are actually what make good, maintainable software. However, repeatable patterns in writing are what make it slop and annoying.\n\nAt its current stage, AI is good at anything with a checkable output. And at things where repeatable patterns are a sign of quality. Software and coding happen to be full of those. Most other work isn’t, especially writing. So if you want a decent result from AI for writing, the best approach right now is not to use it at all.\n\nThanks for reading,[Adlet Balzhanov](https://www.linkedin.com/in/adlet-balzhanov/)\n\nConnect with me on LinkedIn, just use the button below. I read every message. Cheers!", "url": "https://wpnews.pro/news/i-tested-every-al-model-the-same-way-only-one-task-got-better", "canonical_source": "https://www.thetrueengineer.com/p/i-tested-every-ai-model-the-same", "published_at": "2026-08-16 16:04:39+00:00", "updated_at": "2026-08-16 16:10:40.212463+00:00", "lang": "en", "topics": ["artificial-intelligence", "generative-ai", "large-language-models"], "entities": ["Adlet Balzhanov"], "alternates": {"html": "https://wpnews.pro/news/i-tested-every-al-model-the-same-way-only-one-task-got-better", "markdown": "https://wpnews.pro/news/i-tested-every-al-model-the-same-way-only-one-task-got-better.md", "text": "https://wpnews.pro/news/i-tested-every-al-model-the-same-way-only-one-task-got-better.txt", "jsonld": "https://wpnews.pro/news/i-tested-every-al-model-the-same-way-only-one-task-got-better.jsonld"}}