Benjamin Carr, Ph.D. 👨🏻💻🧬<p>Photo <a href="https://hachyderm.io/tags/calorie" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>calorie</span></a> app <a href="https://hachyderm.io/tags/CalAI" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>CalAI</span></a>, downloaded over a million times, was built by two teenagers<br>The concept is simple: Take a picture of the <a href="https://hachyderm.io/tags/food" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>food</span></a> you are about to consume, and let the app log <a href="https://hachyderm.io/tags/calories" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>calories</span></a> and macros for you. Cal AI's advantage, perhaps, is that it was built wholly in the age of large image models. It uses models from Anthropic and OpenAI and RAG to improve accuracy and is trained on open source food calorie and image databases from sites like GitHub. <br><a href="https://techcrunch.com/2025/03/16/photo-calorie-app-cal-ai-downloaded-over-a-million-times-was-built-by-two-teenagers/" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">techcrunch.com/2025/03/16/phot</span><span class="invisible">o-calorie-app-cal-ai-downloaded-over-a-million-times-was-built-by-two-teenagers/</span></a></p>