Sander Schulhoff

speaker

947 appearances 1 recordings 1 series first heard Jun 2025 last heard Jun 2025

Sander Schulhoff’s voice in public audio — every appearance, attributed to the second.

Trend

recordings per month · last 12 months

No recordings in the last 12 months.Older appearances are listed below; set an alert to hear about the next one.

Appearances

newest first · ▶ plays the moment

Lenny's Podcast: Product | Career | Growth · AI prompt engineering in 2025: What works and what doesn’t | Sander Schulhoff (Learn Prompting, HackAPrompt) · 19 Jun 2025 podcast

But at the beginning of my process I was getting little to no accuracy.

Uh it wasn't outputting the codes in a a properly formatted way.

Uh it wasn't really thinking through well uh

how to code the document.

And so what I ended up doing uh was taking uh kind of a

a long list of documents that I went and coded myself or I guess got coded uh and I took those uh and I attached kind of reasonings as to why uh each one was coded in the way it was.

Uh and then I took all of that data and dropped it into my prompt uh and then went ahead and gave the model like a new transcript it had never seen before uh and that boosted the accuracy on that task up by I think like 70%.

So massive, massive performance improvements by having better prompts and doing

was uh actually a bit of a recent development for me uh in terms of kind of thinking through this and explaining it to folks.

But the two modes are

Uh first of all, there's the the conversational mode uh in which most people do prompt engineering.

And that is just you're using Claude, you're using Chat GBT, you say, hey, you know, can you write me this email?

It does kind of a poor job, and you're like, oh no, like make it more formal or add a joke in there, and it adapts its output accordingly.

Uh and so I refer to that as conversational prompt engineering because you're getting

it to improve its output over the course of a conversation.

Uh notably, that is not where the the classical concept of prompt engineering came from.

Uh it actually came uh 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 prompts that are super critical to this product.

I'm running like thousands, millions of inputs through this prompt each day.

Showing 41–60 of 947 · page 3 of 48