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

251–260 of 550 posts

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

#251

Post by nonethewiser »

mentalgear wrote: post #92
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…

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, whereas it would have worked quite well earlier. I don't think this difference is purely semantic.

For whatever it's worth I've never liked the term "prompt engineering." It is perhaps the quintessential example of overusing the word engineering.

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

#252

Post by LASR »

bGl2YW5j wrote: post #193
LASR wrote: post #190

Honestly, GPT-4o is all we ever needed to build a complete human-like reasoning system. I am leading a small team working on a couple of “hard” problems to put the limits of LLMs to the test. One is an options trader. Not algo / HFT, but simply doing due diligence, monitoring the news and making safe long-term bets. Another is an online research and purchasing experience for residential real-estate. Both these tasks,…

What you're describing sounds a lot like traditional training of an ML model combined with descriptive+prescriptive analytics. What value do LLMs bring to this use case?

Ability for normal people to set up reasoning chains.

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

#253

Post by anilgulecha »

tptacek wrote: post #228
risyachka wrote: post #102

Earlier quoted context omitted.

“A month-long skill” after which it won’t be a thing anymore, like so many other.

If you're not writing your own agents, you can skip this skill.

Are you sure? Looking forward - AI is going to be so pervasively used, that understanding what information is to be input will be a general skill. What we've been calling "prompt engineering" - the better ones were actually doing context engineering.

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

#255

Post by Aeolun »

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…

There is only so much you can do with prompts. To go from the 70% accuracy you can achieve with that to the 95% accuracy I see in Claude Code, the context is absolutely the most important, and it’s visible how much effort goes into making sure Claude retrieves exactly the right context, often at the expense of speed.

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

#256

Post by root_axis »

furyofantares wrote: post #123
root_axis wrote: post #59

Earlier quoted context omitted.

I am not a fan of this banal trend of superficially comparing aspects of machine learning to humans. It doesn't provide any insight and is hardly ever accurate.

I've seen a lot of cases where, if you look at the context you're giving the model and imagine giving it to a human (just not yourself or your coworker, someone who doesn't already know what you're trying to achieve - think mechanical turk), the human would be unlikely to give the output you want. Context is often incomplete, unclear, contradictory, or just contains too much distracting information. Those are all thi…

I don't see the usefulness of drawing a comparison to a human. "Context" in this sense is a technical term with a clear meaning. The anthropomorphization doesn't enlighten our understanding of the LLM in any way.

Of course, that comment was just one trivial example, this trope is present in every thread about LLMs. Inevitably, someone trots out a line like "well humans do the same thing" or "humans work the same way" or "humans can't do that either". It's a reflexive platitude most often deployed as a thought-terminating cliche.

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

#257

Post by rTX5CMRXIfFG »

So then for code generation purposes, how is “context engineering” different now from writing technical specs? Providing the LLMs the “right amount of information” means writing specs that cover all states and edge cases. Providing the information “at the right time” means writing composable tech specs that can be interlinked with each other so that you can prompt the LLM with just the specs for the task at hand.

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

#258

Post by simonw »

NoraCodes wrote: post #247
simonw wrote: post #245

Earlier quoted context omitted.

What's happening here is Claude (and ChatGPT alike) have a tool-based search option. You ask them a question - like "who won the Superbowl in 1998" - they then run a search against a classic web search engine (Bing for ChatGPT, Brave for Claude) and fetch back cached results from that engine. They inject those results into their context and use them to answer the question. Using just a few words (the name of the team…

I understand how it works. I think it does not do much to encourage clicking through, because the stated goal is to solve the user's problem without leaving the chat interface (most of the time.)

Yeah, I agree. I actually think an even worse offender here is Google themselves - their AI overview thing answers questions directly on the Google page itself, discouraging site visits. I think that's going to have a really nasty impact on site traffic.

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

#259

Post by arbitrary_name »

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…

From the first link:Read large enough context to ensure you get what you need.

How does this actually work, and how can one better define this to further improve the prompt?

This statement feels like the 'draw the rest of the fucking owl' referred to elsewhere in the thread

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

#260

Post by baxtr »

root_axis wrote: post #59
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…

I am not a fan of this banal trend of superficially comparing aspects of machine learning to humans. It doesn't provide any insight and is hardly ever accurate.

Without my note I wouldn’t have seen this comment, which is very insightful to me at least.

https://news.ycombinator.com/item?id=44429880

Post reply on HN