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

231–240 of 550 posts

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

#231

Post by tptacek »

munificent wrote: post #217

All of these blog posts to me read like nerds speedrunning "how to be a tech lead for a non-disastrous internship". Yes, if you have an over-eager but inexperienced entity that wants nothing more to please you by writing as much code as possible, as the entity's lead, you have to architect a good space where they have all the information they need but can't get easily distracted by nonessential stuff.

Just to keep some clarity here, this is mostly about writing agents. In agent design, LLM calls are just primitives, a little like how a block cipher transform is just a primitive and not a cryptosystem. Agent designers (like cryptography engineers) carefully manage the inputs and outputs to their primitives, which are then composed and filtered.

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

#232

Post by Art9681 »

ZYbCRq22HbJ2y7 wrote: post #83
storus wrote: post #48

Earlier quoted context omitted.

Those issues are considered artifacts of the current crop of LLMs in academic circles; there is already research allowing LLMs to use millions of different tools at the same time, and stable long contexts, likely reducing the amount of agents to one for most use cases outside interfacing different providers. Anyone basing their future agentic systems on current LLMs would likely face LangChain fate - built for GPT-3,…

How would "a million different tool calls at the same time" work? For instance, MCP is HTTP based, even at low latency in incredibly parallel environments that would take forever.

It wouldn't. There is a difference between theory and practicality. Just because we could, doesnt mean we should, especially when costs per token are considered. Capability and scale are often at odds.

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

#233

Post by Art9681 »

tptacek wrote: post #226
coldtea wrote: post #208

Earlier quoted context omitted.

Doesn't change the argument.

It obviously does.

It does not. Context is context no matter how you process it. You can configure tools without MCP or with it. No matter. You still have to provide that as context to an LLM.

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

#234

Post by felipeerias »

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…

If someone asked you about the usages of a particular element in a codebase, you would probably give a more accurate answer if you were able to use a code search tool rather than reading every source file from top to bottom.

For that kind of tasks (and there are many of those!), I don't see why you would expect something fundamentally different in the case of LLMs.

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

#235

Post by shermantanktop »

hobs wrote: post #71
crystal_revenge wrote: post #4

Definitely mirrors my experience. One heuristic I've often used when providing context to model is "is this enough information for a human to solve this task?". Building some text2SQL products in the past it was very interesting to see how often when the model failed, a real data analyst would reply something like "oh yea, that's an older table we don't use any more, the correct table is...". This means the model was…

The thing is, all the people cosplaying as data scientists don't want evaluations, and that's why you saw so little in fake C level projects, because telling people the emperor has no clothes doesn't pay. For those actually using the products to make money well, hey - all of those have evaluations.

I know this proliferation of excited wannabes is just another mark of a hype cycle, and there’s real value this time. But I find myself unreasonably annoyed by people getting high on their own supply and shouting into a megaphone.

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

#237

Post by tptacek »

Art9681 wrote: post #233
tptacek wrote: post #226

Earlier quoted context omitted.

It obviously does.

It does not. Context is context no matter how you process it. You can configure tools without MCP or with it. No matter. You still have to provide that as context to an LLM.

If you're using native tool calls and not MCP, the latency of calls is a nonfactor; that was the concern raised by the root comment.

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

#238

Post by AnotherGoodName »

dosnem wrote: post #212
simonw wrote: post #3

I wrote a bit about this the other day: https://simonwillison.net/2025/Jun/27/context-engineering/ Drew Breunig has been doing some fantastic writing on this subject - coincidentally at the same time as the "context engineering" buzzword appeared but actually unrelated to that meme. How Long Contexts Fail - https://www.dbreunig.com/2025/06/22/how-contexts-fail-and-ho... - talks about the various ways in which longer…

Providing context makes sense to me, but do you have any examples of providing context and then getting the AI to produce something complex? I am quite a proponent of AI but even I find myself failing to produce significant results on complex problems, even when I have clone + memory bank, etc. it ends up being a time sink of trying to get the ai to do something only to have me eventually take over and do it myself.

I had a series of “Using Manim create an animation for formula X rearranging into formula Y with a graph of values of the function”

Beautiful one shot results and i now have really nice animations of some complex maths to help others understand. (I’ll put it up on youtube soon).

I don't know the manim library at all so saved me about a week of work learning and implementing

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

#239

Post by luckydata »

outofpaper wrote: post #33
the_mitsuhiko wrote: post #21

Earlier quoted context omitted.

Drew Breunig's posts are a must read on this. This is not only important for writing your own agents, it is also critical when using agentic coding right now. These limitations/behaviors will be with us for a while.

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.

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

#240

Post by mrits »

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…

Tuning the JVM, compiler optimizations, design patterns, agile methodologies, seo , are just a few things that come to mind
Post reply on HN