Semiconductors are, of course, powering the A.I. revolution. In today's episode, extremely knowledgable and well-spoken Benjamin Hein details how chips are built today... and how they'll be built to support tomorrow's A.I. demands.
Ben is the CEO Merck Electronics, the electronics business at Merck KGaA, Darmstadt, Germany, a 358-year-old science and technology company whose materials end up in nearly every electronic device on the planet.
In this episode, Ben explains:
• Why chips are now going three-dimensional.
• How A.I. helps his team throw out 85% of candidate molecules before they ever reach the lab.
• Why he’s optimistic that A.I. will make high-quality healthcare affordable for everyone in our lifetimes.
• ...and much more!
The SuperDataScience podcast is available on all major podcasting platforms, YouTube, and at SuperDataScience.com.
Filtering by Category: Podcast
In Case You Missed It in October 2026
Wow, check out the guests we had in October! And these big-name guests did not disappoint... ICYMI, today's episode features the best bits of convos we had on air this past month:
1. Dr. Richard Socher (famed A.I. leader, nationally bestselling author and co-founder/CEO of Recursive, which raised a $650m Series A 🤯) explains why recursive self-improvement (RSI) doesn't frighten him the way it frightens so many others.
2. The iconic Carly Taylor (founder of Rebel Data Science; formerly in senior ML leadership positions at Databricks, Microsoft and Activision) tells me how she deliberately chases discomfort to keep growing, and what happens to leaders who are too afraid to admit what they don't know about A.I.
3. Stanford University professor Jeff Hancock and BetterUp Chief Scientist Dr. Kate Niederhoffer coined the term "workslop" in a Harvard Business Review article one year ago. They explain to me why A.I.-generated filler that is harmless on social media becomes infuriating at work.
4. Dr. John L. Renne, Ph.D., AICP, a professor at Tulane University with whom I co-instruct an introductory A.I. course at the school, tells me about a global research project he once thought would be nearly impossible to coordinate (but now can be with A.I.) and why he reckons two hours of his recent work would just a year or two ago needed a half-million-dollar grant (thanks to A.I.)!
The SuperDataScience podcast is available on all major podcasting platforms, YouTube, and at SuperDataScience.com.
AI-Powered Precision Nutrition, with Viome’s Dr. Guru Banavar
Today's guest, Dr. Guruduth Banavar co-founded Viome, a precision-health company that's collected the world's largest human-biology dataset. Hear how they build A.I. models for these data as well as practical health/diet insights!
More on Guru:
• Founding CTO of Viome, whose dataset consists of 100 quadrillion nucleotides from people in more than 150 countries.
• Previously, was the first VP to lead IBM’s Watson A.I. team.
• Holds a PhD in computer science from the University of Utah.
In this episode, Guru explains:
• Why insights on your RNA (rather than your DNA!) is the key to preventing chronic disease. • How Viome’s models predict which foods will spike your blood sugar.
• Why keto dieters look biologically older than vegetarians.
• ...and much more!
The SuperDataScience podcast is available on all major podcasting platforms, YouTube, and at SuperDataScience.com.
Building for the Agent-Native App Store, with Salesforce’s Tyler Carlson
SaaStr Ai, the best-known conference for SaaS businesses, used to have dozens of employees. Today, it runs on just three executives… and an army of AI agents. In this information-rich episode, Tyler Carlson explains how that’s possible. #ad
Tyler:
• Salesforce’s SVP, Head of Product, AgentExchange and Partner Experience, leads Salesforce’s AgentExchange, the unified marketplace to discover, buy, and deploy agents, apps, and capabilities from any surface.
• Holds a degree in math from UC Santa Barbara.
In this episode, Tyler details:
• Salesforce’s new “headless” strategy.
• Why skills and plugins are the new apps.
• How AI practitioners can get what they build in front of Salesforce’s vast customer base.
The SuperDataScience podcast is available on all major podcasting platforms, YouTube, and at SuperDataScience.com.
Connection Is Not Cognition: Why Multi-Agent Systems Silently Fail, with Dr. Vijoy Pandey
Absolutely brilliant Dr. Vijoy Pandey returns to my show for a third time in today's episode. In it, he blows my mind with a record-breaking quantum network in NYC, chips that run on probabilities, and open-source solutions to agent-miscommunication issues.
Vijoy is SVP and General Manager (in other words, the head!) of Outshift by Cisco, which is Cisco's incubation engine.
In a bit more detail, in this episode we discuss:
• How every multi-agent session his team analyzed contained at least one hidden "cognitive failure" and he explains the new open-source protocols Outshift built to keep agents aligned.
• A record-breaking quantum network running on real New York City fiber.
• New chips being built to compute on probabilities instead of zeros and ones.
The SuperDataScience podcast is available on all major podcasting platforms, YouTube, and at SuperDataScience.com.
Cybersecurity for the Agentic AI Era, with Amy Blackshaw
For 4.5 days, autonomous A.I. agents moved through Hugging Face’s infrastructure at one action every 20 seconds. How did they get so far? Exceptional explainer of cybersecurity concepts Amy Blackshaw, CISSP fills us in in today's episode.
Amy is a Senior Vice President at Palo Alto Networks, the world’s largest independent cybersecurity company.
In this episode, Amy explains why frontier A.I. has made the thinking part of a cyberattack nearly free, thereby making cyberattacks inexpensive, fast and relentless, like we saw with the recent Hugging Face breach. Amy magnificently explains cybersecurity and how to protect ourselves and our businesses from cyber threats in the agentic era that’s coming. It is a riveting episode, enjoy!
The SuperDataScience podcast is available on all major podcasting platforms, YouTube, and at SuperDataScience.com.
AI for Real Estate, Walkable Cities and Climate Action, with Prof. John Renne
I recently started an adjunct faculty role at Tulane University, co-teaching an A.I. course alongside Dr. John L. Renne, Ph.D., AICP. In today's episode, brilliant John tells us why he did an A.I. master's *after* becoming a tenured prof... and how it's accelerated his research.
More on John:
• Professor of Real Estate and Urban Planning at Tulane.
• Directs the Tulane real estate development program.
• World-leading expert on walkable communities.
In this episode, John explains:
• How A.I. let him scale up his urban-planning research by orders of magnitude
• How computer vision is playing a role in real estate
• How his startup, OralExam.ai, uses A.I. to tackle the scourge of students’ A.I.-written essays.
The SuperDataScience podcast is available on all major podcasting platforms, YouTube, and at SuperDataScience.com.
Recursive Self-Improvement: The Eureka Machine, with Dr. Richard Socher
In today's exceptional episode, prominent A.I. researcher, entrepreneur and bestselling author Richard Socher details how RSI ("Recursive Self-Improvement") could arrive in as little as a year... and it will herald a new era of scientific breakthroughs.
More on Dr. Socher:
• CEO and co-founder of Recursive, a startup that came out of stealth this year and has already raised over half a billion dollars to build recursively self-improving superintelligence that automates scientific discovery.
• Also co-founder and CEO of the A.I. search engine You.com and a founder of the A.I.-focused venture capital firm AIX Ventures.
• Previously Chief Scientist at Salesforce.
• His brand-new book, "The Eureka Machine", is already a national bestseller.
In this episode, Richard explains:
• How A.I. could deliver a century's worth of scientific breakthroughs in a decade.
• Why fears of an overnight A.I. takeoff ignore physical constraints.
• Which software and jobs will last no matter how capable A.I. becomes.
• ...and much more! This is one of my favorite episodes of the show, don't miss it!
The SuperDataScience podcast is available on all major podcasting platforms, YouTube, and at SuperDataScience.com.
Is AI Holding Kids Back from Learning?
Does A.I. stop kids from learning? New data from thousands of students suggest it depends on how A.I. is used. Below are the details... and the implications for how all of us should be using A.I.!
A.I. USE CAN BE BAD FOR LEARNING
• Researchers tracked 27,000 high-school students in China over 2.5 years, comparing each students results before and after they adopted A.I.
• As shown in the attached chart from The Economist: After adopting A.I., homework scores rose 18% and homework time fell ~30% (from 64 minutes to 45).
• But monthly exam scores fell 20% within six months, and high-stakes entrance-exam scores fell 18-24% after about two years.
• Before LLMs, homework used to predict exam performance... Now the top homework scorers are more likely to do *worse* on exams.
BUT A.I. IS NOT ALWAYS BAD
• Losses were concentrated among the ~80% of A.I. users who blatantly outsourced homework (i.e., very short completion times paired with high scores).
• The small proportion of A.I. users who spent about as long on homework as non-users, however, matched non-users on exams.
• In Turkey, ~1,000 high-school math students using standard GPT-4 scored 17% worse on a later unaided exam than students with no A.I., while a GPT Tutor with learning safeguards erased that penalty.
AND SOMETIMES A.I. CAN BOOST LEARNING!
• A Middlebury College study showed A.I. access raised test scores by 0.27 standard deviations, with gains persisting a week later. Gains were largest among students who had A.I. explain concepts rather than write text.
• A Harvard University study showed a custom A.I. physics tutor (fed lecturers solutions, limited to short responses) more than doubled learning vs an active-learning classroom, in less time.
• A six-week World Bank study in Nigerian after-school programs showed using GPT-4 delivered as part of a comprehensive educational solution showed gains equal to 1.5-2 years of typical schooling.
BOTTOM LINE
Learning requires effortful thinking ("desirable difficulty"). A.I. that hands over answers inflates homework grades and erodes skills; on the other hand, A.I. that explains, hints and gives feedback can be an outstanding tutor.
SO WHAT CAN YOU DO?
1. Watch your kids' time on task: homework quality jumping while time collapses signals outsourcing to A.I.
2. Configure A.I. to tutor, not answer: Turn on the study or learning modes many platforms now offer.
3. Lean on assessments done without A.I. since homework grades no longer show what students know.
4. Apply this to *yourself* at work: Try the problem first, ask the model to explain its reasoning and use A.I. to augment your thinking rather than replace it.
The SuperDataScience podcast is available on all major podcasting platforms, YouTube, and at SuperDataScience.com.
Workslop, Glass Cliffs and Inviting Your Fears to Tea, with Carly Taylor
Over 200,000 people follow her fearless, "unhinged" posts on production A.I. systems, and yet Carly Taylor often can't sleep the night before she speaks on stage. In today's episode, hear why she chases the situations that scare her, including at the A.I. frontier.
More on Carly:
• She is (IMO) the funniest person to follow on LinkedIn.
• Founder of Rebel Data Science.
• Shipped nine Call of Duty titles in five years at Activision, where she led game security.
• Other previous roles include being director of engineering at Microsoft and Field CTO for the gaming vertical at Databricks.
In today's fun and wide-ranging episode, Carly covers:
• Technical A.I. tips.
• General career advice anyone can make use of in these fast-moving times.
• Why she deliberately chases the situations that scare her.
• Why no organization can afford *not* to innovate right now.
• How to use A.I. to sharpen your thinking.
The SuperDataScience podcast is available on all major podcasting platforms, YouTube, and at SuperDataScience.com.
In Case You Missed It in September 2026
September was PACKED with incredible guests having invaluable conversations on my show. ICYMI, today's episode highlights the best bits:
1. The wildly popular data scientist and entrepreneur Aishwarya Srinivasan details which failures a person ought to live through themselves before anyone trusts them to deploy an agent to production.
2. Dr. Luis Serrano, founder of Serrano Academy and author of the bestselling book Grokking Machine Learning, describes "word gravity": that is, how transformer architectures "bend space".
3. Dr. Caitlin Malone, host of the very popular Linear Digressions podcast, fills us in on how A.I. automations brought the show back to life after a five-year hiatus.
4. Dell Technologies' distinguished engineers Ishan S. and Tyler Cox explain why agentic A.I. burns through tokens at a rate that is catching companies out... and what we can do about it.
5. Dr. Dilani Kahawala — a Harvard physics PhD who spent a decade in product leadership at Etsy, Facebook and Atlassian — tells me she has had to throw almost all of that product experience away as she began developing Anna, her always-on A.I. assistant for families. She then walks us through the three problems that turn out to be hardest when your product has no user interface and never stops running.
The SuperDataScience podcast is available on all major podcasting platforms, YouTube, and at SuperDataScience.com.
Workslop: The Hidden Cost of AI-Generated Work, with Prof. Jeff Hancock and Dr. Kate Niederhoffer
That A.I.-written email you fired off to save 10 minutes? It may have cost your colleague an hour... and cost you their trust. Today Prof. Jeff Hancock and Dr. Kate Niederhoffer, coiners of the term "workslop", join me to fix its scourge!
More on Jeff:
• Professor of communication at Stanford University and founding director of the Stanford Social Media Lab.
• Was previously a professor at Cornell University.
• Holds a PhD in psychology from Dalhousie University in Canada.
More on Kate:
• Chief Scientist at BetterUp, a workforce coaching platform that combines human professional coaching, behavioral science, and A.I. to support personal growth, leadership, and mental fitness.
• Holds a PhD in psychology from the The University of Texas at Austin.
Together, Kate and Jeff are prolific co-authors of widely-cited articles on workplace productivity in the A.I. era. They publish in both academic journals and commercially-minded publications like the Harvard Business Review. It was their September 2025 HBR article "A.I.-Generated Workslop is Destroying Productivity" that introduced the world to the now widely-used "workslop" term.
In this episode, Kate and Jeff reveal:
• Why over half of workers admit to producing workslop.
• How it can cost a large company tens of millions of dollars a year.
• Their new concept of "relation slipping".
The SuperDataScience podcast is available on all major podcasting platforms, YouTube, and at SuperDataScience.com.
Agents Need 10x More Data Than Humans, with Salesforce’s CDO Michael Andrew
Four years ago, Salesforce's own customer data were scattered across 650 different data streams and 266 million fragmented profiles, so getting a complete customer picture felt impossible.. My guest today, Salesforce’s Chief Data Officer Michael Andrew, fixed that… and now he's rebuilding it all again for a new kind of customer: AI agents. #ad #SalesforcePartner
More on Michael Andrew:
• Has been at Salesforce for nearly 8 years, eventually growing into the CDO role.
• Has spent nearly three decades listening to customers through data and, at Salesforce, he runs one of the largest Data 360 deployments in the world.
• Previously held a range of analytics and data science leadership roles between San Francisco and London.
In this special episode recorded live at Dreamforce two weeks ago, Michael explains:
• Why agents need ten times more data than humans do.
• Why moving data between warehouses is usually money wasted.
• What data scientists, engineers and analysts should be learning right now as agents (rather than people!) become the main consumers of their work.
The SuperDataScience podcast is available on all major podcasting platforms, YouTube, and at SuperDataScience.com.
Tokenomics: Why Your Agentic AI Bill Is Exploding (and How to Fix It), with Tyler Cox and Ish Shah
Over a single weekend, Ishan S. burned through 2 billion tokens (building a video game for his wife)! He and Tyler Cox join me in today's episode to explain why agentic A.I. bills are exploding... and how a box under your desk can cut them by up to 93%.
Tyler and Ish are returning guests on my podcast... but they are on the show *together* for the first time today. They are both Distinguished Engineers in the Office of the CTO for the client group at Dell Technologies, where they work out how to run powerful A.I. models on the machines closest to you.
In this information-rich episode, Tyler and Ish:
• Dig into "tokenomics" (why agents and their sub-agents devour so many more tokens than chatbots ever did).
• How to pick the right LLM for the job.
• How moving agentic workloads off pay-per-token cloud APIs and onto your own hardware can pay for itself in as little as two months.
The SuperDataScience podcast is available on all major podcasting platforms, YouTube, and at SuperDataScience.com.
Garbage In, Gospel Out: Why Agents Need Better Data, with Salesforce’s Gaurav Pathak
When humans get bad data, we argue about it in meetings. When AI agents get bad data, they can turn it into an answer with total confidence.
My wise guest today, Gaurav Pathak, calls it “garbage in, gospel out.” The takeaway? Better data and context lead to better AI — and, of course, Gaurav has some thoughts on how to get there. #ad #SalesforcePartner
Gaurav Pathak:
• Senior Vice President Product Management AI and Metadata at Salesforce.
• Previously spent 13 years at Informatica building its metadata and AI products, including the CLAIRE AI engine, before Salesforce acquired the company last year.
• Holds a degree in computer science and engineering, as well as an MBA
In this episode, filmed live at Dreamforce in San Francisco last week, Gaurav explains:
• Why context is 95% of the battle for enterprise agents.
• Who the "sin eaters" are that pay for an agent's mistakes.
• The three skills that matter most for AI engineers today.
The SuperDataScience podcast is available on all major podcasting platforms, YouTube, and at SuperDataScience.com.
How AI Brought a Podcast Back From the Dead, with Linear Digressions’ Katie Malone
Dr. Caitlin Malone's extremely popular "Linear Digressions" podcast went silent for five years. Then A.I. made it possible to bring it back... and to manage it like a team. Hear all about effective agent teams in today's excellent episode.
More on Katie:
• Hosts and produces "Linear Digressions", one of the world's most popular data-science podcasts. (It's excellent — check it out!)
• Senior Researcher at Moonlite AI.
• Previously Sr Director of the A.I. Innovation Lab at the Health Care Service Corporation, Sr Director of Data Science at Tempus Labs, and Director of Data Science at Civis Analytics.
• Has taught machine learning via Udacity and at the University of Chicago.
• Holds a PhD in experimental particle physics from Stanford University focused on working with CERN data.
In this episode, Katie explains:
• Why managing people and managing A.I. agents are the same skill in different clothing.
• Why A.I. could hollow out the expertise we need to catch its mistakes.
• A fascinating range of data paradoxes from Simpson’s to Benford’s.
The SuperDataScience podcast is available on all major podcasting platforms, YouTube, and at SuperDataScience.com.
The Chip Built for Agentic AI Inference, with SambaNova’s Anton McGonnell
GPUs are the workhorse of A.I. inference… but they aren’t actually optimized for inference! SambaNova has raised over $2B to build a new chip that is, pushing the frontier of real-time A.I. speed and bandwidth. Hear about it from Anton in today's episode.
More on Anton McGonnell:
• VP of Product at SambaNova, a Bay Area A.I.-hardware business recently valued at $11 billion.
• Was previously Director of Product Management for Machine Learning at UiPath and responsible for A.I. research at Glasswing Ventures.
• Holds an MBA from Harvard Business School and a degree in computer science from Queen's University Belfast.
In today's episode, Anton explains:
• Why agentic A.I. has changed the shape of inference workloads.
• How SambaNova's chip sidesteps the memory bottleneck that slows GPUs when generating output tokens.
The SuperDataScience podcast is available on all major podcasting platforms, YouTube, and at SuperDataScience.com.
OpenAI’s GPT-6 Astra
At GPT-6 Astra's launch, OpenAI president Greg Brockman suggested future observers may point to it as the arrival of AGI. In fact, Artificial Analysis's latest benchmarking suggests it merely catches OpenAI up to Anthropic. Here are the key details:
GPT-6 ASTRA BASICS
• Successor to GPT-5.6 Sol, trained on 100,000+ GPUs at the Stargate facility in Texas.
• It's the first OpenAI model where other A.I. models helped supervise training.
• API pricing is $10/M input tokens and $50/M output (~2.5x Sol's promotional rate; in line with Claude Fable 5.1), with five reasoning-effort settings from low to max.
• Rolled out to ChatGPT Plus, Pro, Business and Enterprise (Enterprise admins must switch it on).
GPT-6 ASTRA CAPABILITIES
• Computer use: 72.6% on OSWorld 2.0 (vs 65.7% for Sol) while finishing tasks ~47% faster.
• Coding: ~58% on Terminal-Bench 4.0 (vs 37% for Sol, ~56% for Fable 5.1), though level with the top Claude models on FrontierCode.
• Math: 99.9% on ARC-AGI-3 (Sol scored under 8%) and 97.6% on FrontierMath Tier 4. Astra also helped tighten a bound on prime gaps from 240 to 186.
• Science: ~65% on Terminal-Bench Science (vs ~22% for Sol, ~53% for Fable 5.1) and ~65% fewer output tokens than Claude Opus 5 on Agents' Last Exam.
• *All of the above stats, however, come from OpenAI themselves.* The third-party view (see chart) shows Astra at 53, tied with Claude Fable 5.1 (and up from Sol's 47) on Artificial Analysis's (widely respected) composite "Intelligence Index".
SAFETY
• First OpenAI model rated "Critical" for cybersecurity under their Preparedness Framework: without safeguards it finds unknown vulnerabilities and builds working exploits (100% on ExploitBench vs 78.5% for Sol; two zero-days found in a fresh Chrome evaluation).
• The release was slowed and gated. The public version supports defensive work but refuses exploit writing; vetted orgs in OpenAI's "Daybreak" program get fewer restrictions.
• New misalignment monitors can pause or halt actions that look unauthorized.
• Encouraging: on a scope-creep evaluation, Sol exceeded its authorized target 48% of the time; Astra did so 0% of the time.
• Concerning: Astra's written reasoning is harder to monitor than Sol's.
IS IT AGI?
• AGI isn't a binary event; there are degrees of breadth and depth (listen to Episode #748 of my podcast for more details).
• BOTTOM LINE: Astra looks like a noteworthy jump in general-intelligence capability for OpenAI relative to their previous flagship model (5.6 Sol), but it does not appear to be moving the frontier toward AGI in any major way... it is merely catching up to Anthropic at the frontier vicinity.
The SuperDataScience podcast is available on all major podcasting platforms, YouTube, and at SuperDataScience.com.
Word Gravity: How Transformers Bend Space, with Dr. Luis Serrano
Today, the renowned A.I. scientist Dr. Luis Serrano (>200k YouTube subs; ex-Apple; ex-Cohere) returns to launch the second edition of his bestselling ML book and for a mind-bending convo on how LLMs "curve space-time".
More on Luis:
• Founder of the Serrano Academy (YouTube channel with over 200,000 subscribers hooked on his visual, intuitive explanations of machine learning).
• Previously worked at Apple, Cohere and the quantum-computing startup Zapata.
• The second edition of his bestselling Manning Publications Co. book "Grokking Machine Learning" is out this month!
In today's episode, Luis details:
• His mind-bending new paper on how transformer architectures mirror Einstein's curved space-time.
• Why RAG isn't an agent.
• How GRPO (the reinforcement-learning technique behind DeepSeek's reasoning breakthrough last year) works.
• ...and much more!
The SuperDataScience podcast is available on all major podcasting platforms, YouTube, and at SuperDataScience.com.
In Case You Missed It in August 2026
If you're in the Northern Hemisphere, summer is drawing to a close... but, ICYMI, today's episode highlights the best bits of the hot hot hot conversations that we had on my podcast in August:
1. In one of the technically richest conversations ever on the show, MongoDB's Field CTO of A.I., Pete Johnson, details the two common traits every company seeing ROI on A.I. investment have.
2. Gurobi Optimization's manager of decision-intelligence strategy Jerry Yurchisin returns to the show to explain where the division of labour between agents and mathematical solvers ought to fall.
3. Priyanka "The Cloud Girl" Vergadia (bestselling author, ex-Google, ex-Microsoft) walks us through how she structures Claude skills so that her output stops being slop.
4. dbt Labs founder and CEO Tristan Handy explains why the semantic layer matters more, not less, now that analytics agents are the ones asking the questions.
The SuperDataScience podcast is available on all major podcasting platforms, YouTube, and at SuperDataScience.com.