Rephonic
Artwork for AE Alignment Podcast

AE Alignment Podcast

James Bowler
AI Alignment
AE Studio
Endogenous Steering Resistance
Self-Monitoring In Llms
Activation Steering
AI Safety
Claude Mythos
Cyber Security
National Security
Self-Interpretation
Bioweapons Uplift Trials
Anthropic
Mechanistic Interpretability
Selfie (activation Interpretation)
Trustworthy AI
United States Government
Evaluations

The AE Alignment Podcast explores the ideas, research, and people working to make advanced AI systems more interpretable, and more aligned. Hosted by James Bowler, the show features conversations with researchers, engineers, and technical leaders at AE Studio and beyond on topics including mechanistic interpretability, model psychology, and approaches to AI alignment. Each episode aims to make cut... more

PublishesTwice monthlyEpisodes8Founded4 months ago
Number of ListenersCategory
Technology

Listen to this Podcast

Artwork for AE Alignment Podcast

Latest Episodes

This episode is a deep dive into a post on Anthropic's research blog: www.anthropic.com/research/off-switch-dual-use

In this episode, James is joined by Ethan Roland, lead author of AE Studio's Gradient Routing paper, to explore a new approa... more

In this episode, James is joined by AE Studio Research Manager Pedro Ávila to discuss transitioning into a career in AI alignment, after Pedro left a 12-year career at Google to work on the problem full time. It’s a practical conversation about how s... more

In this episode, James is joined again by Mike Vaiana, R&D Director at AE Studio, for part two of their conversation on AI alignment. Where part one motivated why alignment matters, this episode goes a layer deeper into what alignment research actual... more

In this episode, James is joined by Stijn Servaes, Lead Research Manager at AE Studio, to break down Anthropic's recently released Claude Mythos preview model and separate genuine signal from hype. This is for listeners who want to actually understan... more

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.

Dwarkesh Podcast
Dwarkesh PodcastDwarkesh Patel
The Ezra Klein Show
The Ezra Klein ShowNew York Times Opinion

Recent Guests

Mike Vaiana
R&D Director at AE Studio
AE Studio
Episode: Mike Vaiana: What is AI Alignment, and Why Should You Care? (Part II)
Stijn Servaes
Lead Research Manager, AE Studio
AE Studio
Episode: Stijn Servaes: Claude Mythos - Superintelligence or Hype?
Adriana Calejo
Director of Government and Strategic Partnerships at AE Studio
AE Studio
Episode: Adriana Calejo: AI Alignment for National Security
Keenan Pepper
Research Scientist at AE Studio
AE Studio
Episode: Keenan Pepper: Self-Interpretation in LLMs

Host

James Bowler
Host of AE Alignment Podcast; Head of Research Partnerships at AE Studio

Chart Rankings

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

Apple Podcasts
#123
Israel/Technology

Talking Points

Recent interactions between the hosts and their guests.

Stijn Servaes: Claude Mythos - Superintelligence or Hype?
Q: Stijn, what's hype and to what extent should we be concerned about Mythos and the claims on the model card?
Stijn argues that while Mythos represents a genuine capability advance and a notable alignment improvement, the hype around it being 'superintelligence' is unwarranted; the real concern lies in how increased scope and autonomy could enable more sophisticated attacks or misuse if safeguards lag behind capability gains.
Mike Vaiana: What is AI Alignment, and Why Should You Care? (Part I)
Q: Why isn't it enough to just tell the AI to be aligned in a prompt?
Because a prompt like be aligned with my goals doesn't reliably constrain the system's behavior; current models can still exhibit unexpected, harmful, or strategically deceptive actions, and alignment needs to be built into the system's objectives and architecture, not just stated in a prompt.
Mike Vaiana: What is AI Alignment, and Why Should You Care? (Part I)
Q: What is AI alignment, in simple terms?
AI alignment is about making sure a highly capable AI system's behavior and goals stay in line with human values and interests, so it doesn't take actions that could harm humans or contradict our priorities as it becomes more autonomous and powerful.
Keenan Pepper: Self-Interpretation in LLMs
Q: Can you walk us through what the vanilla selfie looks like and what you changed to improve upon it with the trained adapter?
Vanilla selfie simply inserts an activation vector as a soft token and asks the model to describe its meaning, which can produce semantically related but often unreliable outputs. The improvement is adding an affine transformation via a trainable adapter while keeping the model frozen, training the adapter to map activations to accurate labels using a labeled dataset, which yields more reliable, relevant interpretations.
Keenan Pepper: Self-Interpretation in LLMs
Q: Awful, but yeah, can you explain at a high level, explain like you're five, the major headline takeaway from the paper?
The headline takeaway is that we can train a lightweight adapter on top of a frozen language model to interpret its own internal activation patterns, effectively translating those hidden states into natural-language explanations that align with the activations and remain connected to the original model.

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 AE Alignment Podcast

What is AE Alignment Podcast about and what kind of topics does it cover?

The show centers on deep-dive conversations with researchers, engineers, and technical leaders focused on AI alignment, interpretability, and safety in frontier AI. Episodes commonly explore mechanistic interpretability, model psychology, evaluation methods, and practical workflows at AE Studio, often touching on governance, deployment risks, and collaborative research with government or industry partners. The tone blends accessible explanations with technical rigor, featuring recurring guests from AE Studio and related research ecosystems, and highlighting concrete examples, ongoing projects, and potential future directions in alignment research. A notable strength is its ability to translate advanced, niche topics into actionable insights... more

Where can I find podcast stats for AE Alignment Podcast?

Rephonic provides a wide range of podcast stats for AE Alignment Podcast. 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 AE Alignment Podcast and access YouTube viewership numbers, download stats, audience demographics, chart rankings, ratings, reviews and more.

How many listeners does AE Alignment Podcast get?

Rephonic provides a full set of podcast information for three million podcasts, including the number of listeners. View further listenership figures for AE Alignment Podcast, 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 AE Alignment Podcast?

Rephonic provides comprehensive predictive audience data for AE Alignment Podcast, 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 AE Alignment Podcast have?

To see how many followers or subscribers AE Alignment Podcast 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 AE Alignment Podcast?

These podcasts share a similar audience with AE Alignment Podcast:

1. Dwarkesh Podcast
2. The Ezra Klein Show

How many episodes of AE Alignment Podcast are there?

AE Alignment Podcast launched 4 months ago and published 8 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 AE Alignment Podcast?

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 AE Alignment Podcast?

Rephonic pulls ratings and reviews for AE Alignment Podcast 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 AE Alignment Podcast?

Rephonic provides full transcripts for episodes of AE Alignment Podcast. 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 AE Alignment Podcast?

Recent guests on AE Alignment Podcast include:

1. Mike Vaiana
2. Stijn Servaes
3. Adriana Calejo
4. Keenan Pepper

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