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

Sometimes it's hard to tell.

Uh, but that's another thing that the the prompt report covers is that uh history of terminology, which is very much of

There's there's certain uh ensembling techniques that are getting a bit more complicated.

And the idea with ensembling is that you have one problem you want to solve, uh, and so it could be a math question.

I'll I'll come back again and again to things like math questions because a lot of these techniques are judged based off of data sets of like math or reasoning questions.

Simply because you're gonna evaluate the accuracy programmatically, uh, as opposed to something like generating interview questions, which is no less valuable, but just very difficult to uh evaluate success for in an automated way.

Ensembling techniques will will take a problem and then you'll have like

Multiple different prompts that go and solve the exact same problem.

Uh so I'll take uh maybe like a a chain of thought prompt, like let's think step by step.

And so I'll give the LM a math problem, I'll give it this prompting technique with the math problem, send it off.

Uh and then a new prompt, new prompting technique, send it off.

And I could do this, you know, with a couple different techniques uh or or more.

And

I'll get back multiple different answers and then I'll take the answer that comes back most commonly.

So it's kind of like if I went to you and Fetty and and Gerson to a bunch of different people and I asked them all the same question.

Uh and they gave me back, you know, slightly different responses, but I kind of take the most common answer as my final answer.

Uh and these are

kind of historically a historically known set of techniques in the AI ML space.

There's lots and lots and lots of ensembling techniques.

Showing 361–380 of 947 · page 19 of 48