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

Uh and then with that list of sub-problems, you can distribute that to all different types of tools.

calling agents if you want to get more complex.

And so after you solve all that, you bring all the information together, and then the main chatbot can make a final decision about whether they can return it and if there's any charges and that sort of thing.

is uh 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 yourself some criticism.

Uh and it goes and does that.

And then you know it gives you this list of criticism and then you can say to it, hey, great criticism.

Why don't you go ahead and implement that?

Uh and then it rewrites its solution.

It outputs something, you get it to criticize itself and then to improve itself.

Uh and so these are you know a pretty notable set of techniques because it's like a I don't know kind of free performance boost that works in some situations.

Uh so that's another kind of favorite uh set of techniques of mine.

How many times can you do this?

Because I could see this happening infinitely.

I guess you could do it infinitely.

I think the model would kind of go crazy at some point.

Just

Showing 241–260 of 947 · page 13 of 48