“Sander is a leading researcher in the field of adversarial robustness”
← All peopleVerified guest
Sander Schulhoff
I'm an artificial intelligence researcher. I've been doing AI research for the last probably like seven years now
2 episodes · 3 sourced appearances
Appearances and evidence
Short attributed excerpts only. Timestamps are approximate.
“I ended up running the first ever generative AI red teaming competition.”
“Today, my guest is Sander Schulhoff.”
Frameworks in these episodes
Episode-linked context, not an unsupported claim of authorship.
Innovation3 steps
Adaptive Evaluation Over Static Benchmarks
Measure AI robustness with attackers that learn, not with a frozen dataset of yesterday's attacks
Read →
Innovation3 steps
CaMeL Permission Pre-Restriction
Grant an agent only the permissions its stated task needs, decided before it runs
Read →
Productivity3 steps
Context Loading (Additional Information)
Front-load all relevant task information — and put it at the top for caching
Read →
Innovation3 steps
Ensembling (Mixture of Reasoning Experts)
Solve the same problem several ways and take the most common answer
Read →
Productivity3 steps
Few-Shot Prompting
Show the model examples of what good looks like instead of describing it
Read →
Productivity3 steps
Prompt Decomposition
Make the model list the sub-problems first, then solve each before the whole
Read →
Strategy5 steps
Prompt Injection Defense Stack
Stop trying to fix injection with prompts and guardrails — mitigate at the model level
Read →
Productivity3 steps
Self-Criticism Loop
Get the model to critique its own answer, then implement its own critique
Read →
Strategy3 steps
The AI Deployment Risk Triage
Classify any AI deployment into one of three risk tiers before spending a dollar on defense
Read →
Strategy5 steps
The AI Security Vendor Due-Diligence Test
Five questions that expose whether an AI guardrail vendor is selling real protection or theater
Read →
Mindset3 steps
The Angry-God Containment Lens
Assume the AI is a malicious agent trying to hurt you, then engineer so it structurally can't
Read →
Resources in their episodes
- 1883
- Airbnb
- Anthropic
- Apple Podcasts
- Atlas
- Bolt
- ChatGPT
- Claude
- Claude Code
- Comet
- Cursor
- Datadog
- Daylight Computer DC-1
- Devin
- Don't Write That Jailbreak Paper
- Ender's Game
- Eppo
- Evil
- Gemini
- GitHub Copilot
- GPT-3
- GPT-4o
- GPT-5
- Granola
- Hack Prompt and Learn Prompting AI Security Course
- Hugging Face
- Lenny's Newsletter
- Lenny's Podcast
- lennyspodcast.com
- Lovable
- Maven
- Metronome
- OpenAI
- reMarkable
- Repello AI
- Replit
- Scale AI
- ServiceNow
- Spotify
- Stripe
- The River of Doubt
- v0
- Vanta
- Windsurf
- Y Combinator
- Yellowstone
Related guests
Spot an error or want this profile removed? Request a correction or removal.