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

481–490 of 550 posts

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

#481

Post by 8n4vidtmkvmk »

ironmagma wrote: post #297
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.

What is all software but tinkering? I mean this not as an insult to software dev but to work generally. It’s all play in the end.

I don't buy this. With software engineering you can generally make incremental progress towards your goal. Yes, sometimes you have to scrap stuff, but usually not the entire thing because an LLM spout out pure nonsense.

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

#482

Post by smokel »

phkahler wrote: post #407
StevenWaterman wrote: post #380

Earlier quoted context omitted.

Yep, every AI call is essentially just asking it to predict what the next word is after: You are a helpful assistant. Why is the sky blue? Because of Rayleigh scattering. The blue light refracts more. Why is it red at sunset then? And we keep repeating that until the next word is ` `, then extract the bit in between the last assistant tags, and return it. The AI has been trained to look at ` ` differently to ` `, but…

This is why I enjoy calling AI "autocomplete" when people make big claims about it - because that's where it came from and exactly what it is.

Depending on what you mean exactly, "autocomplete" and big claims are not mutually exclusive.

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

#484

Post by argestes »

jedimastert wrote: post #369
ozgung wrote: post #319

Earlier quoted context omitted.

Why not? What is so special about reasoning that you cannot achieve by predicting tokens aka. constructing sentences?

Predicting tokens and constructing sentences are not the same thing. It cannot create its own sentences because it does not have a self

What is the definition of self in this context? What makes a human have a self?

(I agree with you. I'm thinking the Ahamkara for the humans. I'm curious about your definition)

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

#485

Post by aleksiy123 »

asadotzler wrote: post #199
aleksiy123 wrote: post #44

Earlier quoted context omitted.

It may not be a silver bullet, in that it needs lots of low level human guidance to do some complex task. But looking at the trend of these tools, the help they are requiring is become more and more higher level, and they are becoming more and more capable of doing longer more complex tasks as well as being able to find the information they need from other systems/tools (search, internet, docs, code etc...). I think…

why is it that so many of you think there's anything meaningfully predictable based on these past trends? what on earth makes you belive the line keeps going as it has, when there's literally nothing to base that belief on. it's all just wishful thinking.

It doesn't have to keep going up forever.

All you have to believe is that there is still room for iterative improvement on the current.

I'm not saying that this is going to lead to AGI or exponential improvements.

All I'm saying is that the iterative progression is there and there are still plenty of room for ideas and improvement.

For example look at something like copilot.

First it was just chat, then inline code editing, then hooking up tools like search.

Then multi file editing, agents.

But there still plenty of space here to improve not with just better models but better tools and integrations. Why stop now?

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

#486

Post by BoiledCabbage »

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 (…

> >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.

Maybe it's true for computer science - but most people on here aren't doing computer science. They're doing software engineering. And it sure as heck isn't true for software engineering. If it were, I wouldn't be hearing arguments about programming languages for years, or static vs dynamic typing, or functional vs OOP...

So what you're arguing about AI isn't exactly anything new to software development.

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

#487

Post by jcon321 »

simonw wrote: post #87
jcon321 wrote: post #81

I thought this entire premise was obvious? Does it really take an article and a venn diagram to say you should only provide the relevant content to your LLM when asking a question?

"Relevant content to your LLM when asking a question" is last year's RAG. If you look at how sophisticated current LLM systems work there is so much more to this. Just one example: Microsoft open sourced VS Code Copilot Chat today (MIT license). Their prompts are dynamically assembled with tool instructions for various tools based on whether or not they are enabled: https://github.com/microsoft/vscode-copilot-chat/bl…

Okay fair point, thank you for that info. This makes more sense for the people who are developing prompt generation for some tool (like copilot, claude code, etc) yet I was thinking of it more from a user standpoint (like asking chatgpt, gemini, etc).

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

#488

Post by bigfishrunning »

dysoco wrote: post #249
bgwalter wrote: post #139

These discussions increasingly remind me of gamers discussing various strategies in WoW or similar. Purportedly working strategies found by trial and error and discussed in a language that is only intelligible to the in-group (because no one else is interested). We are entering a new era of gamification of programming, where the power users force their imaginary strategies on innocent people by selling them to the eq…

> 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.

Dijkstra is rolling in his grave. Computer Science was a rigorous sub-field of mathematics before the tech bros showed up and started moving fast and breaking things. The endless supply of VC money has destroyed this field.

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

#489

Post by grogenaut »

FeepingCreature wrote: post #386
lblume wrote: post #365

Earlier quoted context omitted.

I have uploaded entire books to the latest Gemini and had the model reliably accurately answer specific questions requiring knowledge of multiple chapters.

I think it works for info but not so well for instructions/guidance. That's why the standard advice is instructions at the start and repeated at the end.

Or under the covers are just putting all the text you fed at into a rag database and doing embedding search define route and snippets and answer your questions when asked directly. Which is the difference approach than recalling instructions

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

#490

Post by Davidzheng »

LtWorf wrote: post #455
Davidzheng wrote: post #441

Earlier quoted context omitted.

OK I, like the other commenter, also feel stupid to reply to zingers--but here goes. First of all, I think a lot of the issue here is this sense of baggage over this word intelligence--I guess because believing machines can be intelligent goes against this core belief that people have that humans are special. This isn't meant as a personal attack--I just think it clouds thinking. Intelligence of an agent is a spectru…

So according to your extremely broad definition of intelligence, also a casio calculator is intelligent? Sure, if we define anything as intelligent, AI is intelligent. Is this definition somehow helpful though?

It's not binary...
Post reply on HN