embraceai meetup

Author: ZanSara

content/talks/2025-11-06-embrace-ai-meetup-reasoning-models.md

@@ -1,7 +1,14 @@
 ---
-title: "[UPCOMING] Embrace:AI // 2025.06 - Reasoning LLMs & Multimodal Architecture"
+title: "Embrace:AI // 2025.06 - Reasoning LLMs & Multimodal Architecture"
 date: 2025-11-06
 author: "ZanSara"
 featuredImage: "/talks/2025-11-06-embrace-ai-meetup-reasoning-models.png"
-externalLink: "https://www.meetup.com/embrace-ai/events/311629934/"
 ---
+
+[Announcement](https://www.meetup.com/embrace-ai/events/311629934/), [slides](https://drive.google.com/file/d/1QoUVlA915-7UJqu9DkxKQUc3deJhsB8t/view?usp=sharing).
+All resources can also be found in 
+[my archive](https://docs.google.com/presentation/d/1RzJOwSwaLcNFkkPuvpR9e9pRzf0mnz23l8H29X9UDSA/edit?usp=drive_link).
+
+---
+
+At [Embrace.ai's November Meetup](https://www.meetup.com/embrace-ai/), part of the [Lisbon AI Week](https://lisbonaiweek.com/) I talked about reasoning models: what they are, what they aren't, how they work and when to use them. Is GPT-5 AGI? Is it an AI Agent? Or is it just a glorified chain-of-thought prompt under the hood? To answer these questions, I classified LLMs into a small "taxonomy" based on the post-training steps they go through, in order to highlight how reasoning models differ qualitatively from their predecessors just like instruction-tuned models were not simple text-completion models with a better prompt. I also covered the effect of increasing the reasoning effort of the model, clarifying when it's useful and when it can lead to overthinking.