964: In Case You Missed It in January 2026
In this first of the year ICYMI episode, Jon Krohn selects his favorite moments from January’s SuperDataScience interviews. Listen to why incentivizing workers is the best way to get them to disclose their use of AI tools and pave the way for an AI-forward future, how AI continues to mimic human development in its own evolution, the importance of evaluation in building AI systems, and how to keep your best employees (and also: how to know your value) with guests Sadie St. Lawrence, Ashwin Rajeeva, Sinan Ozdemir, Vijoy Pandey, and Ethan Mollick.
Additional materials: www.superdatascience.com/964
Interested in sponsoring a SuperDataScience Podcast episode? Email natalie@superdatascience.com for sponsorship information.
959: Building Agents 101: Design Patterns, Evals and Optimization (with Sinan Ozdemir)
AI entrepreneur and bestselling author Sinan Ozdemir speaks to Jon Krohn about the practical differences between agentic AI and AI workflows, why evaluating accuracy on its own won’t tell you enough about AI models, and more about his latest book Building Agentic AI.
This episode is brought to you by the Dell, by Intel, by Fabi and by Cisco.
Additional materials: www.superdatascience.com/959
Interested in sponsoring a SuperDataScience Podcast episode? Email natalie@superdatascience.com for sponsorship information.
In this episode you will learn:
(04:57) Exploring the differences between workflows and agents
(17:03) How to work out parameter count for a given task
(25:26) The best way to evaluate LLMs
(33:12) How to run hybrid workflow + agentic projects effectively
903: LLM Benchmarks Are Lying to You (And What to Do Instead), with Sinan Ozdemir
Has AI benchmarking reached its limit, and what do we have to fill this gap? Sinan Ozdemir speaks to Jon Krohn about the lack of transparency in training data and the necessity of human-led quality assurance to detect AI hallucinations, when and why to be skeptical of AI benchmarks, and the future of benchmarking agentic and multimodal models.
Additional materials: www.superdatascience.com/903
This episode is brought to you by Trainium2, the latest AI chip from AWS, by Adverity, the conversational analytics platform and by the Dell AI Factory with NVIDIA.
Interested in sponsoring a SuperDataScience Podcast episode? Email natalie@superdatascience.com for sponsorship information.
In this episode you will learn:
(16:48) Sinan’s new podcast, Practically Intelligent
(21:54) What to know about the limits of AI benchmarking
(53:22) Alternatives to AI benchmarks
(1:01:23) The difficulties in getting a model to recognize its mistakes
784: Aligning Large Language Models, with Sinan Ozdemir
Aligning LLMs: How can we teach pre-trained LLMs to hold a conversation and learn new information from each other? This was where Sinan Ozdemir began his investigation into aligning LLMs. In this episode, he talks to Jon Krohn about the limitations of definitions for LLMs, training LLMs, and whether it is possible to train an LLM without alignment.
Additional materials: www.superdatascience.com/784
Interested in sponsoring a SuperDataScience Podcast episode? Visit passionfroot.me/superdatascience for sponsorship information.
445: Conversational A.I.
Sinan Ozdemir joins us to share his work in conversational AI and what it takes to keep chatbots up to date and functional in an ever-changing world.
In this episode you will learn:
Kylie.ai under Directly [4:51]
Sinan’s day-to-day work and tools [10:45]
Use cases [18:27]
AutoML’s role in these processes [21:55]
What hard or soft skills are needed for this work? [29:32]
Sinan’s background in teaching [34:58]
Sinan’s history in pure math and applied math [39:44]
Sinan’s math tattoos [43:48]
Additional materials: www.superdatascience.com/445
333: BERT and NLP in 2020 and Beyond
Sinan Ozdemir is back again, this time talking about his work since his company Kylie.ai was acquired by Directly. We discuss his work, the way he is creating human and AI synergy and the future of NLP as it continues to progress.
In this episode you will learn:
Sinan’s company acquired [7:29]
Explainable deep learning models [16:13]
Airbnb case study [19:42]
Microsoft case study [22:25]
Sinan’s role at Directly [25:57]
Work with Sinan [32:57]
Preview of Sinan at DSGO [38:38]
BERT [43:18]
Sinan’s prediction for NLP in 2020 [53:17]
Additional materials: www.superdatascience.com/333
161: Using AI to Automate Communication
In this episode of the SuperDataScience Podcast, I chat with the Founder and Chief Technology Officer of Kylie.AI, Sinan Ozdemir. You will hear about Feature Engineering and why it is vital in interpreting and analyzing data models; you will also hear about Automated Customer Care Services and its importance in the future of enterprises, and get insights on why humans should ensure that AI is ethically responsible when serving humanity.
If you enjoyed this episode, check out show notes, resources, and more at www.superdatascience.com/161
021: Applications of Data Science, Democratizing AI and Advice with Sinan Ozdemir
In this episode of the SuperDataScience Podcast, I chat with Data Science Author Sinan Ozdemir. You will learn the different applications of data science, advance your knowledge in democratizing AI and hear advices that will help the learners of data science.
If you enjoyed this episode, check out show notes, resources, and more at www.superdatascience.com/21