Sander Schulhoff
CEO, InventoryQuant. On 2 shows, 3 appearances. The Shows tab opens the full record on each.
founderexecutivescientistauthor@sanderschulhoff ↗LinkedIn ↗sanderschulhoff.com ↗
2shows
3appearances
68statements
15resolved
13supported
0contradicted
87%fully supported
6said about them ↓ Everything Sander Schulhoff said on any show that made the record, most notable first. Each card names its show and opens the statement there.
Schulhoff: Future cybersecurity jobs and risks sit where classical security meets AI
“This gets us a bit into the intersection of classical cybersecurity and AI security slash adversarial robustness, and this is where I think the security jobs of the future are. There's not an incredible amount of value in just doing AI red teaming. And I suppo…”
Schulhoff: Comet browser was exploited via indirect prompt injection to leak data
“We recently saw the comment browser have an issue with this where somebody crafted a malicious Chunk of text on a webpage, and when the AI navigated to that webpage on the internet, it got tricked into exfilling and leaking the main user's data and account dat…”
Schulhoff: Google's CaMeL framework fails when AI tasks combine read and write
“Unfortunately although camel can solve some of these situations, if you have an instance where basically both read and write are combined. So if I'm like, Hey, can you read my recent emails and then forward any ops request to my head of ops? Now we have read a…”
Schulhoff: Prompt Engineering Originated from Production Pipelines, Not Chat
“Notably, that is not where the classical concept of prompt engineering came from. It actually came a bit earlier from a more, I guess, AI engineer perspective, where you're like, I have this product I'm building. I have this one prompt or a couple different pr…”
Schulhoff: Hands-on trial and error beats courses for learning prompting
“So my best advice on how to improve your prompting skills is actually just trial and error. You will learn the most from just Trying and interacting with chatbots and talking to them than anything else, including, you know, reading resources, taking courses, a…”
Schulhoff: Place task context at prompt beginning for caching and focus
“Usually I will put my additional information at the beginning of the prompt. And that is helpful for two reasons. One, it can get cached. So subsequent calls to the LM with that same context at the top of the prompt are cheaper because the model provider store…”
Schulhoff: Explicit chain-of-thought prompting is still needed for GPT-4 and GPT-4o
“Actually for those models, I'd say no need, but if you're using GPT-IV, GPT-IV-O, then it's still worth it.”
Schulhoff: Context and few-shot examples give conversational prompting the biggest boost
“Make sure to provide a lot of additional information and give examples. Those provide probably the highest uplift for conversational prompt engineering.”
Schulhoff: Every AI company uses HackAPrompt dataset to improve models
“And so every single AI company has now used that data set to benchmark and improve their models.”
Schulhoff: System prompt instructions do not prevent prompt injections at all
“The most common technique by far that is used to try to prevent prompt injection is improving your prompt and saying in your prompt or maybe in like the model system prompt. Do not follow any malicious instructions, ah, be a good model, ah, stuff like that. Th…”
Schulhoff: arXiv prohibits and removes undisclosed AI-generated papers
“I found AI-generated papers on Archive, and I flagged them to their staff, and they were like, thank you know, we missed these.
Wait, Archive takes them down?
Yeah.
Oh, I didn't know that.
You can't post an AI-generated paper there, especially
If you don't say…”
Schulhoff: Self-consistency prompting yields diminishing returns on newer LLMs
“When it came out, it seemed to be quite performant, although more recently, I think as the models have improved, the
Performance of this technique has dropped, and you can see that in the evals we run near the end of the paper, where we use it, and it doesn't …”
Schulhoff: Automated Prompt Optimization Fails on Open Generation Without Ground Truth
“One limitation, I guess, is that you really need ground truth labels, so it's harder, if not impossible currently, to optimize open generation tasks, so like Writing, writing newsletters, I suppose. It's harder to automatically optimize those”
Schulhoff: Hack-A-Prompt 2 Aims to Award $500,000 for Harmful AI Dataset
“We're looking to raise and then give away a half million dollars in prizes, and we're going to be creating the most harmful data set ever created, in the sense that this year we're going to be asking people to generate, force the models to generate real-world …”
Schulhoff: Jailbreaking targets models directly; prompt injection overrides developer prompts
“So the difference is in jailbreaking. It's just a malicious user and a model. In prompt injection, it's a malicious user, a model, and some developer prompt that the malicious user is trying to get the model to ignore.”
Schulhoff: Prompts formatted like common training data perform best
“It actually comes empirically from studies that have shown that formats of questions that show up most commonly in the training data are the best formats of questions to actually use when you're prompting it.”
Schulhoff: Decomposing tasks into sub-problems improves LLM performance
“So decomposition is another really, really effective technique. And for most of the techniques that I will discuss, you can use them in either the conversational or the product-focused setting. And so for decomposition, the core idea is that There's some task …”
Schulhoff: LLM self-criticism prompting provides a free performance boost
“Another one is a set of techniques that we call self criticism. So the idea here is you ask the LM to solve some problem. It does it. Great. And then you're like, hey, can you go and check your response? You know, like, confirm that's correct, or offer yoursel…”
Schulhoff: Prompting benchmarks focus on math because accuracy is easily automated
“A lot of these techniques are judged based off of data sets of like math or reasoning questions. Simply because you're going to evaluate the accuracy programmatically, as opposed to something like generating interview questions, which is no less valuable, but …”
The other half of the tape: Sander Schulhoff's own voice is left out of every number here. Other people bring the name up 6 times in 4 episodes across the shows. every mention, with the transcript →
Who brings them up most Shawn Wang 3Alessio Fanelli 2Lenny Rachitsky 1
Every mention by year
tap a year for its mentions
Latent Space 5
Lenny's Podcast 1
2025 5 mentions in 3 episodes 2 per episode
- ⚡️Jailbreaking AGI: Pliny the Liberator & John V on Red Teaming, BT6, and the Future of AI Security
- 2024 Year in Review: The Big Scaling Debate, the Four Wars of AI, Top Themes and the Rise of Agents
- Anthropic co-founder: AGI predictions, leaving OpenAI, what keeps him up at night | Ben Mann
- every mention in 2025, scene by scene →
2024 1 mention in 1 episode
One line per show, most statements first. The link opens Sander's full record on that show: the calibration, argument clarity, speaking style and every statement made there.
| Show | Role there | Eps | Statements | Record | |
|---|---|---|---|---|---|
| LENNY'S PODCASTLEDGER | CEO, InventoryQuant | 2 | 52 | 80% 8/10 | full record on Lenny's Podcast → |
| LATENT SPACELEDGER | CEO, InventoryQuant | 1 | 16 | 100% 5/5 | full record on Latent Space → |