Mapping the Mind of a Neural Net: Goodfire’s Eric Ho on the Future of Interpretability
Eric Ho is building Goodfire to solve one of AI’s most critical challenges: understanding what’s actually happening inside neural networks. His team is developing techniques to understand, audit and edit neural networks at the feature level. Eric discusses breakthrough results in resolving superposition through sparse autoencoders, successful model editing demonstrations and real-world applications in genomics with Arc Institute's DNA foundation models. He argues that interpretability will be critical as AI systems become more powerful and take on mission-critical roles in society.
Hosted by Sonya Huang and Roelof Botha, Sequoia Capital
Mentioned in this episode:
Mech interp: Mechanistic interpretability, list of important papers here
Phineas Gage: 19th century railway engineer who lost most of his brain’s left frontal lobe in an accident. Became a famous case study in neuroscience.
Human Genome Project: Effort from 1990-2003 to generate the first sequence of the human genome which accelerated the study of human biology
Emergent Misalignment: Narrow finetuning can produce broadly misaligned LLMs
Zoom In: An Introduction to Circuits: First important mechanistic interpretability paper from OpenAI in 2020
Superposition: Concept from physics applied to interpretability that allows neural networks to simulate larger networks (e.g. more concepts than neurons)
Apollo Research: AI safety company that designs AI model evaluations and conducts interpretability research
Towards Monosemanticity: Decomposing Language Models With Dictionary Learning. 2023 Anthropic paper that uses a sparse autoencoder to extract interpretable features; followed by Scaling Monosemanticity
Under the Hood of a Reasoning Model: 2025 Goodfire paper that interprets DeepSeek’s reasoning model R1
Auto-interpretability: The ability to use LLMs to automatically write explanations for the behavior of neurons in LLMs
Interpreting Evo 2: Arc Institute's Next-Generation Genomic Foundation Model. (see episode with Arc co-founder Patrick Hsu)
Paint with Ember: Canvas interface from Goodfire that lets you steer an LLM’s visual output in real time (paper here)
Model diffing: Interpreting how a model differs from checkpoint to checkpoint during finetuning
Feature steering: The ability to change the style of LLM output by up or down weighting features (e.g. talking like a pirate vs factual information about the Andromeda Galaxy)
Weight based interpretability: Method for directly decomposing neural network parameters into mechanistic components, instead of using features
The Urgency of Interpretability: Essay by Anthropic founder Dario Amodei
On the Biology of a Large Language Model: Goodfire collaboration with Anthropic
--------
47:07
--------
47:07
ElevenLabs’ Mati Staniszewski: Why Voice Will Be the Fundamental Interface for Tech
Mati Staniszewski, co-founder and CEO of ElevenLabs, explains how staying laser-focused on audio innovation has allowed his company to thrive despite the push into multimodality from foundation models. From a high school friendship in Poland to building one of the fastest-growing AI companies, Mati shares how ElevenLabs transformed text-to-speech with contextual understanding and emotional delivery. He discusses the company's viral moments (from Harry Potter by Balenciaga to powering Darth Vader in Fortnite), and explains how ElevenLabs is creating the infrastructure for voice agents and real-time translation that could eliminate language barriers worldwide.
Hosted by: Pat Grady, Sequoia Capital
Mentioned in this episode:
Attention Is All You Need: The original Transformers paper
Tortoise-tts: Open source text to speech model that was a starting point for ElevenLabs (which now maintains a v2)
Harry Potter by Balenciaga: ElevenLabs’ first big viral moment from 2023
The first AI that can laugh: 2022 blog post backing up ElevenLab’s claim of laughter (it got better in v3)
Darth Vader's voice in Fortnite: ElevenLabs used actual voice clips provided by James Earl Jones before he died
Lex Fridman interviews Prime Minister Modi: ElevenLabs enabled Fridman to speak in Hindi and Modi to speak in English.
Time Person of the Year 2024: ElevenLabs-powered experiment with “conversational journalism”
Iconic Voices: Richard Feynman, Deepak Chopra, Maya Angelou and more available in ElevenLabs reader app
SIP trunking: a method of delivering voice, video, and other unified communications over the internet using the Session Initiation Protocol (SIP)
Genesys: Leading enterprise CX platform for agentic AI
Hitchhiker’s Guide to the Galaxy: Comedy/science-fiction series by Douglas Adams that contains the concept of the Babel Fish instantaneous translator, cited by Mati
FYI: communication and productivity app for creatives that Mati uses, founded by will.i.am
Lovable: prototyping app that Mati loves
--------
59:53
--------
59:53
From DevOps ‘Heart Attacks’ to AI-Powered Diagnostics With Traversal’s AI Agents
Anish Agarwal and Raj Agrawal, co-founders of Traversal, are transforming how enterprises handle critical system failures. Their AI agents can perform root cause analysis in 2-4 minutes instead of the hours typically spent by teams of engineers scrambling in Slack channels. Drawing from their academic research in causal inference and gene regulatory networks, they’ve built agents that systematically traverse complex dependency maps to identify the smoking gun logs and problematic code changes. As AI-generated code becomes more prevalent, Traversal addresses a growing challenge: debugging systems where humans didn’t write the original code, making AI-powered troubleshooting essential for maintaining reliable software at scale.
Hosted by Sonya Huang and Bogomil Balkansky, Sequoia Capital
Mentioned in this episode:
SRE: Site reliability engineering. The function within engineering teams that monitors and improves the availability and performance of software systems and services.
Golden signals: four key metrics used by Site Reliability Engineers (SREs) to monitor the health and performance of IT systems: latency, traffic, errors and saturation.
MELT data: Metrics, events, log, and traces. A framework for observability.
The Bitter Lesson: Another mention of Nobel Prize winner Rich Sutton’s influential post.
--------
40:32
--------
40:32
The Breakthroughs Needed for AGI Have Already Been Made: OpenAI Former Research Head Bob McGrew
As OpenAI's former Head of Research, Bob McGrew witnessed the company's evolution from GPT-3’s breakthrough to today's reasoning models. He argues that there are three legs of the stool for AGI—Transformers, scaled pre-training, and reasoning—and that the fundamentals that will shape the next decade-plus are already in place. He thinks 2025 will be defined by reasoning while pre-training hits diminishing returns. Bob discusses why the agent economy will price services at compute costs due to near-infinite supply, fundamentally disrupting industries like law and medicine, and how his children use ChatGPT to spark curiosity and agency. From robotics breakthroughs to managing brilliant researchers, Bob offers a unique perspective on AI’s trajectory and where startups can still find defensible opportunities.
Hosted by: Stephanie Zhan and Sonya Huang, Sequoia Capital
Mentioned in this episode:
Solving Rubik’s Cube with a robot hand: OpenAI’s original robotics research
Computer Use and Operator: Anthropic and OpenAI reasoning breakthroughs that originated with OpenAi researchers
Skild and Physical Intelligence: Robotics-oriented companies Bob sees as well-positioned now
Distyl: AI company founded by ex-Palintir alums to create enterprise workflows driven by proprietary data
Member of the technical staff: Title at OpenAI designed to break down barriers between AI researchers and engineers
Howie.ai: Scheduling app that Bob uses
--------
48:51
--------
48:51
OpenAI Codex Team: From Coding Autocomplete to Asynchronous Autonomous Agents
Hanson Wang and Alexander Embiricos from OpenAI's Codex team discuss their latest AI coding agent that works independently in its own environment for up to 30 minutes, generating full pull requests from simple task descriptions. They explain how they trained the model beyond competitive programming to match real-world software engineering needs, the shift from pairing with AI to delegating to autonomous agents, and their vision for a future where the majority of code is written by agents working on their own computers. The conversation covers the technical challenges of long-running inference, the importance of creating realistic training environments, and how developers are already using Codex to fix bugs and implement features at OpenAI.
Hosted by Sonya Huang and Lauren Reeder, Sequoia Capital
Mentioned in this episode:
The Culture: Sci-Fi series by Iain Banks portraying an optimistic view of AI
The Bitter Lesson: Influential paper by Rich Sutton on the importance of scale as a strategic unlock for AI.
Join us as we train our neural nets on the theme of the century: AI. Sonya Huang, Pat Grady and more Sequoia Capital partners host conversations with leading AI builders and researchers to ask critical questions and develop a deeper understanding of the evolving technologies—and their implications for technology, business and society.
The content of this podcast does not constitute investment advice, an offer to provide investment advisory services, or an offer to sell or solicitation of an offer to buy an interest in any investment fund.
UK