←back to thread

Context Engineering for Agents

(rlancemartin.github.io)
114 points 0x79de | 2 comments | 01 Jul 25 10:56 UTC | HN request time: 0.461s | source
Show context
ares623 ◴[04 Jul 25 05:22 UTC] No.44461351[source]▶
Another article handwaving or underselling the effects of hallucination. I can't help but draw parallels to layer 2 attempts from crypto.
replies(1): >>44462031 #
FiniteIntegral ◴[04 Jul 25 07:27 UTC] No.44462031[source]▶
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 engineering" and pretending it's anything different is ignorant at best and destructively dumb at worst.

replies(7): >>44462128 #>>44462410 #>>44462950 #>>44464219 #>>44464240 #>>44464924 #>>44465232 #
OJFord ◴[04 Jul 25 09:43 UTC] No.44462950[source]▶
Let's just call all aspects of LLM usage 'x-engineering' to professionalise it, even while we're barely starting to figure it out.
replies(1): >>44463885 #
1. antonvs ◴[04 Jul 25 12:18 UTC] No.44463885[source]▶
It’s fitting, since the industry is largely driven by hype engineering.
replies(1): >>44465329 #
2. klabb3 ◴[04 Jul 25 15:23 UTC] No.44465329[source]▶
It’s not good for engineering with the dilution of the term. We don’t really have many backup terms to switch to.

Maybe we should look to science and start using the term pseudo-engineering to dismiss the frivolous terms. I don’t really like that though since pseudoscience has an invalidating connotation whereas eg prompt engineering is not a lesser or invalid form of engineering - it’s simply not engineering at all, and no more or less ”valid”. It’s like calling yourself a ”canine engineer” when teaching your dog to do tricks.