Large Reasoning Models
We’ve all heard about LLMs.
What about Large Reasoning Models, or LRMs?
Models like OpenAI’s o1 and o3 are still a bit mysterious. o1 “thinks before it answers” and was “trained with reinforcement learning to perform complex reasoning” [Ref]
We understand from prompt engineering how Chain of Thought [Ref] and Self-Refine [Ref] work. In fact, leveraging these patterns are part of doing best-practice prompt engineering!
This type of “chain of thought reasoning in context” produces strong performance across difficult benchmarks including those focused on safety.
LRMs like o1 and o3 improve with both “train-time compute” (e.g., reinforcement learning) and “test-time compute” (e.g. time spent thinking).
As of last month, Google also got into the game of reasoning models, with Gemini 2.0 Flash Thinking Experimental, which is “trained to use thoughts to strengthen its reasoning.”
How should we think about leveraging LRMs to introduce reasoning in our application workflows in 2025? Is the additional latency and thinking time worth the gains in performance?
What are the implications for “hidden chains of thought” that allow us to “read the mind” of the model and understand its thought process? Do they really effectively fact-check themselves?
Join us live for this special event where we’ll do a few demos and have a rich discussion around how reasoning capabilities are being built directly into LLMs.
Bring your questions and comments to join the discussion live!
📚 You’ll learn:
What we know from OpenAI’s o1 system card
Where LRMs are making an impact today, and when you should think about using them in your workflows
🤓 Who should attend the event:
Aspiring AI Engineers who want to build with the latest LLMs on the market
AI Engineering leaders who want to understand where to leverage LRMs in the enterprise
Speakers:
Dr. Greg” Loughnane is the Co-Founder & CEO of AI Makerspace, where he is an instructor for their AI Engineering Bootcamp. Since 2021, he has built and led industry-leading Machine Learning education programs. Previously, he worked as an AI product manager, a university professor teaching AI, an AI consultant and startup advisor, and an ML researcher. He loves trail running and is based in Dayton, Ohio.
Chris “The Wiz” Alexiuk is the Co-Founder & CTO at AI Makerspace, where he is an instructor for their AI Engineering Bootcamp. During the day, he is also a Developer Advocate at NVIDIA. Previously, he was a Founding Machine Learning Engineer, Data Scientist, and ML curriculum developer and instructor. He’s a YouTube content creator YouTube who’s motto is “Build, build, build!” He loves Dungeons & Dragons and is based in Toronto, Canada.
Follow AI Makerspace on LinkedIn and YouTube to stay updated about workshops, new courses, and corporate training opportunities.