{"slug": "who-cares-about-the-model", "title": "Who Cares About the Model?", "summary": "Amp shipped the Dial two weeks ago, changing the default model from Claude Opus 4.8 to GPT-5.6 Sol, and 69% of Dial users never switched from the medium setting. The company received zero complaints despite the overnight switch from Anthropic to OpenAI, as the differences between frontier models are now small enough that they don't visibly change results for individual tasks. Amp CEO argues that task difficulty, context, and review have more impact on output than the specific model used.", "body_md": "Two weeks ago [we shipped the Dial](https://ampcode.com/news/the-dial) and quietly did something that's supposed to be traumatic: we changed the default model.\n\nBefore the Dial, Amp's default mode was `smart`\n\n, running Claude Opus 4.8 and carrying more than half of all new threads. The Dial made `medium`\n\nthe default, and `medium`\n\nruns GPT-5.6 Sol.\n\nMost Amp users switched from Anthropic to OpenAI overnight.\n\nWe braced for the outcry. Every model swap in every coding tool comes with one. We prepared migration docs, packaged the old modes as [installable plugins](https://ampcode.com/modes), and waited.\n\nNothing happened. Not a single complaint.\n\nHere's what the switch looked like in production:\n\nThe day before the Dial shipped, `smart`\n\ncarried 55% of new threads. A week later: zero. Last week, the four Dial modes carried 93% of all new threads, and `medium`\n\nalone carried two-thirds. Of the users on the Dial, 69% never set it to anything but `medium`\n\n.\n\nAnd the Amp plugins we shipped to bring the old modes back — exact prompts, exact models, one command to get `smart`\n\nagain? Almost nobody installed them.\n\nThe differences between frontier models are now small. Small enough that for one engineer on one task, switching models won't visibly change the result.\n\nBut they still matter to us, here at Amp: across every thread on every tier, small differences compound, so we keep benchmarking and swapping models. That's the trade. The default is good because someone is paid to care about it, and it doesn't have to be you.\n\nWhat does change your output are three things, none of which is a model: how hard the task is, what context you put in, and how closely you review what comes out. All three have more impact on the outcome than whether you use this or that latest frontier model.\n\nThe Dial covers the first one: how hard the task is. You tell it how hard the task is and the corresponding setting on the Dial uses whichever model wins it right now, re-tested constantly. You know your tasks, we know the models.\n\nAnd for the other two — the context and the review — the rest of Amp lets you do the best job with that.", "url": "https://wpnews.pro/news/who-cares-about-the-model", "canonical_source": "https://ampcode.com/news/who-cares-about-the-model", "published_at": "2026-07-29 00:00:00+00:00", "updated_at": "2026-07-29 15:55:56.807160+00:00", "lang": "en", "topics": ["artificial-intelligence", "large-language-models", "ai-products", "developer-tools"], "entities": ["Amp", "Claude Opus 4.8", "GPT-5.6 Sol", "Anthropic", "OpenAI", "The Dial"], "alternates": {"html": "https://wpnews.pro/news/who-cares-about-the-model", "markdown": "https://wpnews.pro/news/who-cares-about-the-model.md", "text": "https://wpnews.pro/news/who-cares-about-the-model.txt", "jsonld": "https://wpnews.pro/news/who-cares-about-the-model.jsonld"}}