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

Context Engineering for Agents

rlancemartin.github.io

Post reply on HN
Print view View original

31–36 of 36 posts

Re: Context Engineering for Agents

#31

Post by truth_seeker »

hnlmorg wrote: post #8
truth_seeker wrote: post #4

Nah ! I am not convinced that context engineering is better (in the long trem) than prompt engineering. Context engineering is still complex and needs maintainance. Its much lower level than human level language. Given that domain expertise of the problem statment, we can apply the same tactics in context engineering on higher level in prompt engineering.

This whole industry is complex and needs constant maintenance. APIs break all the time -- and that's assuming they were even correct to begin with. New models are constantly released, each with their own new quirks. People are still figuring out how to build this tech -- and as quickly as they figure one thing out, the goal posts move again. This entire field is basically being built on quicksand. And it will stay li…

Agreed. but making ENGLISH or any human speakable language as main interface shoul be given highest priority IMHO !

Re: Context Engineering for Agents

#32

Post by truth_seeker »

CharlieDigital wrote: post #21
truth_seeker wrote: post #4

Nah ! I am not convinced that context engineering is better (in the long trem) than prompt engineering. Context engineering is still complex and needs maintainance. Its much lower level than human level language. Given that domain expertise of the problem statment, we can apply the same tactics in context engineering on higher level in prompt engineering.

Going to disagree here. Early in the game when context windows were very small (8k, 16k, and then 32k), the team I was working with achieved fantastic results with very low incidence of hallucinations through deep "context engineering" (we didn't call it that but rather "indexing and retrieval"). We did a project for Alibaba and generated tens of thousands of pieces of output . They actually had human analysts review…

Are we on the same page ?

Whats really stopping you to parse and prioritise CUSTOM CONTEXT if given as text instruction in prompt engineering.

Re: Context Engineering for Agents

#33

Post by triyambakam »

skeeter2020 wrote: post #24
FiniteIntegral wrote: post #6

Earlier quoted context omitted.

Apple released a paper showing the diminishing returns of "deep learning" specifically when it comes to math. For example, it has a hard time solving the Tower of Hanoi problem past 6-7 discs, and that's not even giving it the restriction of optimal solutions. The agents they tested would hallucinate steps and couldn't follow simple instructions. On top of that -- rebranding "prompt engineering" as "context engineeri…

We used to call both of these "being good with the Google". Equating it to engineering is both hilarious and insulting.

It is a stretch but not semantically wrong. Strictly, engineering is the practical application of science; we could say that the study of the usage of a model is indeed science and so by applying this science it is engineering.

Re: Context Engineering for Agents

#34

Post by lend000 »

I'm consistently amazed by how great the first response from o3-pro deep research is, and then consistently disappointed by response number 5 or so if I continue the conversation. Better context management is the most important bottleneck in LLMs, and it seems like a robust solution would involve modifying the transformer architecture itself instead of using context limited LLMs to manage the context for other LLMs.

Re: Context Engineering for Agents

#35

Post by CharlieDigital »

truth_seeker wrote: post #32
CharlieDigital wrote: post #21

Earlier quoted context omitted.

Going to disagree here. Early in the game when context windows were very small (8k, 16k, and then 32k), the team I was working with achieved fantastic results with very low incidence of hallucinations through deep "context engineering" (we didn't call it that but rather "indexing and retrieval"). We did a project for Alibaba and generated tens of thousands of pieces of output . They actually had human analysts review…

Are we on the same page ? Whats really stopping you to parse and prioritise CUSTOM CONTEXT if given as text instruction in prompt engineering.

That's why indexing and retrieval is perhaps the better term. Custom context doesn't exist unless a team makes it so.

Re: Context Engineering for Agents

#36

Post by sgt101 »

nico wrote: post #30
sgt101 wrote: post #25

I read these things and I think : this can never work. This is passing a huge set of parameters to a probabilistic map function.. one token changes and you get a completely useless result.

Maybe, but also, some of the most popular ai-assisted coding / vibecoding platforms are using system prompts that are 1.5k+ lines long[0] 0: https://github.com/x1xhlol/system-prompts-and-models-of-ai-t...

But is there any evidence that these system prompts really work?

How are the different components of these prompts contributing to the result... what happens if one word is changed? what about two words?

Post reply on HN