Rephonic
Artwork for How AI Is Built

How AI Is Built

Nicolay Gerold
Supabase
Postgresql
Data Architecture
Vector Databases
Machine Learning
AI Applications
Hybrid Search
Carbon
BEM
Real-Time Processing
PG Vector
Data Processing
Quantization
Multi-Vector Support
Data Orchestration
Lancedb
Llms
Data Transformation
Orioledb
Authentication

Real engineers. Real deployments. Zero hype. We interview the top engineers who actually put AI in production. Learn what the best engineers have figured out through years of experience. Hosted by Nicolay Gerold, CEO of Aisbach and CTO at Proxdeal and Multiply Content.

PublishesTwice monthlyEpisodes63Founded2 years ago
Number of ListenersCategory
Technology

Listen to this Podcast

Artwork for How AI Is Built

Latest Episodes

Nicolay here,

Most AI coding conversations focus on which model to use. This one focuses on workflow - the specific commands, git strategies, and review processes that let one engineer ship production code with AI agents doing 80% of the work.

Toda... more

Nicolay here,

while everyone races to cloud-scale LLMs, Pete Warden is solving AI problems by going completely offline. No network connectivity required.

Today I have the chance to talk to Pete Warden, CEO of Useful Sensors and author of the TinyML... more

YouTube

Nicolay here,most AI conversations focus on training bigger models with more compute. This one explores the counterintuitive world where averaging weights from different models creates better performance than expensive post-training.

Today I have th... more

YouTube

Nicolay here,

Most AI coding tools obsess over automating everything. This conversation focuses on the right

balance between human skill and AI assistance - where manual context beats web search every time.

Today I have the chance to talk to Ben H... more

YouTube

Key Facts

Accepts Guests
Contact Information
Podcast Host
Number of Listeners
Find out how many people listen to this podcast per episode and each month.

Similar Podcasts

People also subscribe to these shows.

Recent Guests

Kieran Klaassen
Founder of Cora and one of the Entrepreneurs in Residence at Avery.
Cora
Episode: #056 Building Solo: How One Engineer Uses AI Agents to Ship Production Code
Pete Warden
CEO of Useful Sensors and author of the TinyML book
Useful Sensors
Episode: #055 Embedding Intelligence: AI's Move to the Edge
Ben Holmes
Software Engineer at Warp
Warp
Episode: #053 AI in the Terminal: Enhancing Coding with Warp
Paul Iusztin
Author of the LLM Engineers Handbook and founder of Decoding ML
Decoding ML
Episode: #050 Bringing LLMs to Production: Delete Frameworks, Avoid Finetuning, Ship Faster
Dexter Horthy
Founder of HumanLayer
HumanLayer
Episode: #048 Why Your AI Agents Need Permission to Act, Not Just Read
Jorge Arango
An expert in information architecture
Episode: #047 Architecting Information for Search, Humans, and Artificial Intelligence
Marek Galovic
Former engineer at PyCon, now building a new kind of search database at TopK
TopK
Episode: #046 Building a Search Database From First Principles
John Berryman
Formerly worked on Eventbrite Search, GitHub Code Search, and GitHub Co-Pilot. Author of a book on prompt engineering.
Episode: #045 RAG As Two Things - Prompt Engineering and Search
Kuzu Guest
Expert in database technology, particularly graph databases
Kuzu
Episode: #044 Graphs Aren't Just For Specialists Anymore

Host

Nicolay Gerold
Host and CEO of Aisbach, CTO at Proxdeal and Multiply Content. Engages discussions focused on practical AI applications and deployment strategies.

Reviews

4.9 out of 5 stars from 35 ratings
  • Comprehensive course on modern information retrieval

    Informative interviews with a range of industry experts in Information Retrieval (IR)

    Apple Podcasts
    5
    Dgreen74
    United Statesa year ago
  • Great Pod

    Worth a listen if you are in the AI space.

    Apple Podcasts
    5
    Mikoo231
    United Statesa year ago

Listeners Say

Key themes from listener reviews, highlighting what works and what could be improved about the show.

Worth a listen if you are in the AI space.
Informative interviews with a range of industry experts in Information Retrieval (IR).

Chart Rankings

How this podcast ranks in the Apple Podcasts, Spotify and YouTube charts.

Apple Podcasts
#239
Belgium/Technology

Talking Points

Recent interactions between the hosts and their guests.

#054 Building Frankenstein Models with Model Merging and the Future of AI
Q: What are the main reasons why you merge models?
Firstly, to create a better checkpoint from different model training phases and secondly, to combine capabilities of different task-specific models.
#054 Building Frankenstein Models with Model Merging and the Future of AI
Q: How did you get into AI and engineering?
I started my journey with a PhD focused on network-based intrusion detection systems using machine learning.
#051 Build systems that can be debugged at 4am by tired humans with no context
Q: What practices have you found most impactful for normal engineers?
Having engineers own their code in production helps create feedback loops which are necessary for understanding and improving systems.
#050 Bringing LLMs to Production: Delete Frameworks, Avoid Finetuning, Ship Faster
Q: What are your first steps when tackling LLM projects?
Paul describes his approach of setting up a Python project template and focusing on an end-to-end process rather than on accuracy initially.
#050 Bringing LLMs to Production: Delete Frameworks, Avoid Finetuning, Ship Faster
Q: How did you get into AI or engineering of all?
Paul shares his journey, starting as a software engineer and his initial passion for AI, leading him through various roles including deep learning research and practical applications.

Audience Metrics

Listeners, social reach, demographics and more for this podcast.

Listeners per Episode
Gender Skew
Location
Interests
Professions
Age Range
Household Income
Social Media Reach

Frequently Asked Questions About How AI Is Built

What is How AI Is Built about and what kind of topics does it cover?

Offering a grounded perspective on the development and deployment of artificial intelligence, this series features in-depth discussions with leading engineers who share their insights and experiences from real-world AI projects. Topics frequently addressed include the practical challenges faced in model deployment, infrastructure considerations, and innovations such as AI integration in coding environments. There is a clear focus on providing listeners with actionable knowledge about AI systems and technologies, emphasizing a no-nonsense approach that contrasts with the often exaggerated narratives surrounding AI. Unique elements include discussions on advanced programming techniques, ethical implications of AI, and the evolution of softwar... more

Where can I find podcast stats for How AI Is Built?

Rephonic provides a wide range of podcast stats for How AI Is Built. We scanned the web and collated all of the information that we could find in our comprehensive podcast database. See how many people listen to How AI Is Built and access YouTube viewership numbers, download stats, audience demographics, chart rankings, ratings, reviews and more.

How many listeners does How AI Is Built get?

Rephonic provides a full set of podcast information for three million podcasts, including the number of listeners. View further listenership figures for How AI Is Built, including podcast download numbers and subscriber numbers, so you can make better decisions about which podcasts to sponsor or be a guest on. You will need to upgrade your account to access this premium data.

What are the audience demographics for How AI Is Built?

Rephonic provides comprehensive predictive audience data for How AI Is Built, including gender skew, age, country, political leaning, income, professions, education level, and interests. You can access these listener demographics by upgrading your account.

How many subscribers and views does How AI Is Built have?

To see how many followers or subscribers How AI Is Built has on Spotify and other platforms such as Castbox and Podcast Addict, simply upgrade your account. You'll also find viewership figures for their YouTube channel if they have one.

Which podcasts are similar to How AI Is Built?

These podcasts share a similar audience with How AI Is Built:

1. Practical AI
2. Dwarkesh Podcast
3. The Changelog: Software Development, Open Source

How many episodes of How AI Is Built are there?

How AI Is Built launched 2 years ago and published 63 episodes to date. You can find more information about this podcast including rankings, audience demographics and engagement in our podcast database.

How do I contact How AI Is Built?

Our systems regularly scour the web to find email addresses and social media links for this podcast. We scanned the web and collated all of the contact information that we could find in our podcast database. But in the unlikely event that you can't find what you're looking for, our concierge service lets you request our research team to source better contacts for you.

Where can I see ratings and reviews for How AI Is Built?

Rephonic pulls ratings and reviews for How AI Is Built from multiple sources, including Spotify, Apple Podcasts, Castbox, and Podcast Addict.

View all the reviews in one place instead of visiting each platform individually and use this information to decide if a show is worth pitching or not.

How do I access podcast episode transcripts for How AI Is Built?

Rephonic provides full transcripts for episodes of How AI Is Built. Search within each transcript for your keywords, whether they be topics, brands or people, and figure out if it's worth pitching as a guest or sponsor. You can even set-up alerts to get notified when your keywords are mentioned.

What guests have appeared on How AI Is Built?

Recent guests on How AI Is Built include:

1. Kieran Klaassen
2. Pete Warden
3. Ben Holmes
4. Paul Iusztin
5. Dexter Horthy
6. Jorge Arango
7. Marek Galovic
8. John Berryman

To view more recent guests and their details, simply upgrade your Rephonic account. You'll also get access to a typical guest profile to help you decide if the show is worth pitching.

Find and pitch the right podcasts

We help savvy brands, marketers and PR professionals to find the right podcasts for any topic or niche. Get the data and contacts you need to pitch podcasts at scale and turn listeners into customers.
Try it free for 7 days