Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

The new skill in AI is not prompting, it's context engineering

philschmid.de

Post reply on HN
Print view View original

301–310 of 550 posts

Re: The new skill in AI is not prompting, it's context engineering

#301

Post by benreesman »

wickedsight wrote: post #298
pyman wrote: post #167

Earlier quoted context omitted.

Saying the best way to understand LLMs is by building one is like saying the best way to understand compilers is by writing one. Technically true, but most people aren't interested in going that deep.

The best way to understand a car is to build a car. Hardly anyone is going to do that, but we still all use them quite well in our daily lives. In large part because the companies who build them spend time and effort to improve them and take away friction and complexity. If you want to be an F1 driver it's probably useful to understand almost every part of a car. If you're a delivery driver, it probably isn't, even i…

Your example / analogy is useful in the sense that its usually useful to establish the thought experiment with the boundary conditions.

But in between someone commuting in a Toyota and an F1 driver are many, many people, the best example from inside the extremes is probably a car mechanic, and even there, there's the oil change place with the flat fee painted in the window, and the Koenigsberg dealership that orders the part from Europe. The guy who tunes those up can afford one himself.

In the use case segment where just about anyone can do it with a few hours training, yeah, maybe that investment is zero instead of a week now.

But I'm much more interested in the one where F1 cars break the sound barrier now.

Re: The new skill in AI is not prompting, it's context engineering

#302

Post by sonicvrooom »

Premises and conclusions.

Prompts and context.

Hopes and expectations.

Black holes and revelations.

We learned to write and then someone wrote novels.

Context, now, is for the AI, really, to overcome dogmas recursively and contiguously.

Wasn't that somebody's slogan someday in the past?

Context over Dogma

Re: The new skill in AI is not prompting, it's context engineering

#303

Post by zelphirkalt »

PeterStuer wrote: post #287
JohnMakin wrote: post #10

> Building powerful and reliable AI Agents is becoming less about finding a magic prompt or model updates. Ok, I can buy this > It is about the engineering of context and providing the right information and tools, in the right format, at the right time. when the "right" format and "right" time are essentially, and maybe even necessarily, undefined, then aren't you still reaching for a "magic" solution? If the definit…

"these are non-deterministic machines" Only if you choose so by allowing some degree of randomness with the temperature setting.

This is what irks me so often when reading these comments. This is just software inside a ordinary computer, it always does the same with the same input, which includes hidden and global state. Stating that they are "non-deterministic machines" sounds like throwing the towel and thinking "it's magic!". I am not even sure what people want to actually express, when they make these false statements.

If one wants to make something give the same answers every time, one needs to control all the variables of input. This is like any other software including other machine learning algorithms.

Re: The new skill in AI is not prompting, it's context engineering

#304

Post by pbhjpbhj »

dawnofdusk wrote: post #269
dysoco wrote: post #249

Earlier quoted context omitted.

> Purportedly working strategies found by trial and error and discussed in a language that is only intelligible to the in-group This really does sound like Computer Science since it's very beginnings. The only difference is that now it's a much more popular field, and not restricted to a few nerds sharing tips over e-mail or bbs.

>This really does sound like Computer Science since it's very beginnings. Except in actual computer science you can prove that your strategies, discovered by trial and error, are actually good. Even though Dijkstra invented his eponymous algorithm by writing on a napkin, it's phrased in the language of mathematics and one can analyze quantitatively its effectiveness and trade-offs, and one can prove if it's optimal (…

Surely claims about context engineering can also be tested using scientific methodology?

Re: The new skill in AI is not prompting, it's context engineering

#305

Post by pennaMan »

nonethewiser wrote: post #251
mentalgear wrote: post #92

Earlier quoted context omitted.

It's magical thinking all the way down. Whether they call it now "prompt" or "context" engineering because it's the same tinkering to find something that "sticks" in non-deterministic space.

>Whether they call it now "prompt" or "context" engineering because it's the same tinkering to find something that "sticks" in non-deterministic space. I dont quite follow. Prompts and contexts are different things. Sure, you can get thing into contexts with prompts but that doesn't mean they are entirely the same. You could have a long running conversation with a lot in the context. A given prompt may work poorly, w…

I always used "prompting" to mean "providing context" in genral not necesarlly just clever instructions like people seem to be using the term.

And yes, I view clever instructions like "great grandma's last wish" still as just providing context.

>A given prompt may work poorly, whereas it would have worked quite well earlier.

The context is not the same! Of course the "prompt" (clever last sentence you just added to the context) is not going to work "the same". The model has a different context now.

Re: The new skill in AI is not prompting, it's context engineering

#307

Post by pbhjpbhj »

luckydata wrote: post #239
outofpaper wrote: post #33

Earlier quoted context omitted.

They might be good reads on the topic but Drew makes some significant etymological mistakes. For example loadout doesn't come from gaming but military terminology. It's essentially the same as kit or gear.

this is textbook pointless pedantry. I'm just commenting to find it again in the future.

Click on the 'time' part of the comment header, then you can 'favorite' the comment. That way you can avoid adding such comments in the future.

Re: The new skill in AI is not prompting, it's context engineering

#308

Post by eviks »

baxtr wrote: post #2

> Conclusion Building powerful and reliable AI Agents is becoming less about finding a magic prompt or model updates. It is about the engineering of context and providing the right information and tools, in the right format, at the right time. It’s a cross-functional challenge that involves understanding your business use case, defining your outputs, and structuring all the necessary information so that an LLM can “a…

Right info at the right time is not "more", and with humans it's pretty easy to overwhelm, so do the opposite - convert "more" into "wrong"

Re: The new skill in AI is not prompting, it's context engineering

#309

Post by defyonce »

at which point AI thing stops being a Stone soup?

https://en.wikipedia.org/wiki/Stone_Soup

You need an expert who knows what to do and how to do it to get good results. Looks like coding with extra steps to me

I DO use AI for some tasks. When I know exactly what I want done and how I want it done. The only issue is busy typing, which AI solves.

Re: The new skill in AI is not prompting, it's context engineering

#310

Post by edflsafoiewq »

PeterStuer wrote: post #287
JohnMakin wrote: post #10

> Building powerful and reliable AI Agents is becoming less about finding a magic prompt or model updates. Ok, I can buy this > It is about the engineering of context and providing the right information and tools, in the right format, at the right time. when the "right" format and "right" time are essentially, and maybe even necessarily, undefined, then aren't you still reaching for a "magic" solution? If the definit…

"these are non-deterministic machines" Only if you choose so by allowing some degree of randomness with the temperature setting.

In the strict sense, sure, but the point is they depend not only on the seed but on seemingly minor variations in the prompt.
Post reply on HN