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

211–220 of 550 posts

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

#211

Post by ModernMech »

simonw wrote: post #140
mikhmha wrote: post #137

Earlier quoted context omitted.

It is total quackery. When you zoom out in these discussions you begin to see how the AI yappers and their methodology is just modern-day alchemy with its own jargon and "esoteric" techniques.

See my comment here. These new context engineering techniques are a whole lot less quackery than the prompting techniques from last year: https://news.ycombinator.com/item?id=44428628

The quackery comes in the application of these techniques, promising that they "work" without ever really showing it. Of course what's suggested in that blog sounds rational -- they're just restating common project management practices.

What makes it quackery is there's no evidence to show that these "suggestions" actually work (and how well) when it comes to using LLMs. There's no measurement, no rigor, no analysis. Just suggestions and anecdotes: "Here's what we did and it worked great for us!" It's like the self-help section of the bookstore, but now we're (as an industry) passing it off as technical content.

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

#212

Post by dosnem »

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.

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

#213

Post by TZubiri »

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…

Rediscovering encapsulation

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

#214

Post by layer8 »

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…

The difference is that humans can actively seek to acquire the necessary context by themselves. They don't have to passively sit there and wait for someone else to do the tedious work of feeding them all necessary context upfront. And we value humans who are able to proactively do that seeking by themselves, until they are satisfied that they can do a good job.

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

#215

Post by coliveira »

FridgeSeal wrote: post #177
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 just AI people moving the goalposts now that everyone has realised that “prompt engineering” isn’t a special skill.

In other words, "if AI doesn't work for you the problem is not IA, it is the user", that's what AI companies want us to believe.

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

#216

Post by coliveira »

sarchertech wrote: post #209
coderatlarge wrote: post #152

Earlier quoted context omitted.

i tend to share your view. but then your comment describes a lot of previous cycles of enterprise software selling. it’s just that this time is reaching a little uncomfortably into the builder’s /developer’s traditional areas of influence/control/workflow. how devs feel now is probably how others (ex csr, qa, sre) felt in the past when their managers pushed whatever tooling/practice was becoming popular or sine qua n…

This has been happening to developers for years. 25 years ago it was object oriented programming.

The difference is that with OO there was at least hope that a well trained programmer could make it work. Nowadays, any person who understands how AI knows that's near impossible.

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

#217

Post by munificent »

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.

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

#218

Post by refulgentis »

dbreunig wrote: post #197
refulgentis wrote: post #182

Earlier quoted context omitted.

I agree - what distinguishes this is how rushed and self-aware it is. It is being pushed top down, sheepishly. EDIT: Ah, you also wrote the blog posts tied to this. It gives 0 comfort that you have a blog post re: building buzz phrases in 2020, rather, it enhances the awkward inorganic rush people are self-aware of.

I studied linguistic anthropology, in addition to CS. Been at it since 2002. And I wrote the first post before the meme.

I've read these ideas a 1000 times, I thought it was the most beautiful core of the "Sparks of AGI" paper. (6.2)

We should be able to name the source of this sheepishness and have fun with that we are all things at once: you can be a viral hit 2002 super PhD with expertise in all areas involved in this topic that has brought pop attention onto something important, and yet, the hip topic you feel centered on can also make people's eyes roll temporarily. You're doing God's work. The AI = F(C) thing is really important. Its just, in the short term, it will feel like a buzzword.

This is much more about me playing with, what we can reduce to, the "get off my lawn!" take. I felt it interesting to voice because it is a consistent undercurrent in the discussion and also leads to observable absurdities when trying to describe it. It is not questioning you, your ideas, or work. It has just come about at a time when things become hyperreal hyperquickly and I am feeling old.

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

#219

Post by inspectorwadget »

CamperBob2 wrote: post #192
inspectorwadget wrote: post #117

Earlier quoted context omitted.

>any more than we have to look at the machine language emitted by a C compiler. Some developers do actually look at the output of C compilers, and some of them even spend a lot of time criticizing that output by a specific compiler (even writing long blog posts about it). The C language has an ISO specification, and if a compiler does not conform to that specification, it is considered a bug in that compiler. You can…

Some developers do actually look at the output of C compilers, and some of them even spend a lot of time criticizing that output by a specific compiler (even writing long blog posts about it). The C language has an ISO specification, and if a compiler does not conform to that specification, it is considered a bug in that compiler. Those programmers don't get much done compared to programmers who understand their tool…

For the record, I did not downvote anyone.

>[Inspecting assembly and caring about its output]

I agree that it does not make sense for everyone to inspect generated assembly code, but for some jobs, like compiler developers, it is normal to do so, and for some other jobs it can make sense to do so occassionally. But, inspecting assembly was not my main point. My main point was that a lot of people, probably many more than those that inspect assembly code, care about the generated code. If a C compiler does not conform to the C ISO specification, a C programmer that does not inspect assembly can still decide to file a bug report, due to caring about conformance of the compiler.

The scenario you describe, as I understand it at least, of codebases where they are so complex and quality requirements are so low that inspecting code (not assembly, but the output from LLMs) is unnecessary, or mitigation strategies are sufficient, is not consistent with a lot of existing codebases, or parts of codebases. And even for very large and messy codebases, there are still often abstractions and layers. Yes, there can be abstraction leakage in systems, and fault tolerance against not just software bugs but unchecked code, can be a valuable approach. But I am not certain it would make sense to have even most code be unchecked (in the sense of having been reviewed by a programmer).

I also doubt a natural language would replace a programming language, at least if verification or AGI is not included. English and Mandarin are ambiguous. C and assembly code is (meant to be) unambiguous, and it is generally considered a significant error if a programming language is ambiguous. Without verification of some kind, or an expert (human or AGI), how could one in general cases use that code safely and usefully? There could be cases where one could do other kinds of mitigation, but there are at least a large proportion of cases where I am skeptical that sole mitigation strategies would be sufficient.

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

#220

Post by simonw »

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.

Quite a few times, I've been able to give it enough context to write me an entire working piece of software in a single shot. I use that for plugins pretty often, eg this:

  llm -m openai/o3 \
    -f https://raw.githubusercontent.com/simonw/llm-hacker-news/refs/heads/main/llm_hacker_news.py \
    -f https://raw.githubusercontent.com/simonw/tools/refs/heads/main/github-issue-to-markdown.html \
    -s 'Write a new fragments plugin in Python that registers issue:org/repo/123 which fetches that issue
      number from the specified github repo and uses the same markdown logic as the HTML page to turn that into a fragment'
Which produced this: https://gist.github.com/simonw/249e16edffe6350f7265012bee9e3...
Post reply on HN