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

311–320 of 550 posts

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

#311

Post by pbhjpbhj »

Attention Is Everything.

To direct attention properly you need the right context for the ML model you're doing inference with.

This inference manipulation -- prompt and/or context engineering -- reminds me of Socrates (as written by Plato) eliciting from a boy seemingly unknown truths [not consciously realised by the boy] by careful construction of the questions.

See Anamnesis, https://en.m.wikipedia.org/wiki/Anamnesis_(philosophy). I'm saying it's like the [Socratic] logical process and _not_ suggesting it's philosophically akin to anamnesis.

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

#312

Post by walterfreedom »

defyonce wrote: post #309

at which point AI thing stops being a Stone soup? https://en.wikipedia.org/wiki/Stone_Soup You need an expert who knows what to do and how to do it to get good results. Looks like coding with extra steps to me I DO use AI for some tasks. When I know exactly what I want done and how I want it done. The only issue is busy typing, which AI solves.

AI is already very impressive for natural language formatting and filtering, we use it for ratifying profiles and posts. and it takes around like an hour to implement this from scratch, and there are no alternatives that can do the same thing as comprehensively anyways

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

#315

Post by shakna »

groestl wrote: post #282
ffsm8 wrote: post #263

Earlier quoted context omitted.

Yeah, if anything it should be called an art. The term engineering makes little sense in this context, but really... Did it make sense for eg "QA Engineer" and all the other jobs we tacked it on, too? I don't think so, so it's kinda arguing after we've been misusing the term for well over 10 yrs

Well, to get the right thing into the context in a performant way when you dealing with a huge dataset is definitely engineering.

Engineering tends to mean "the application of scientific and mathematical principles to practical ends".

I'm not sure there's much scientific or mathematical about guessing how a non-deterministic system will behave.

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

#317

Post by evjan »

andy99 wrote: post #121
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 called over-fitting, that's basically what prompt engineering is.

That doesn't sound like how I understand over-fitting, but I'm intrigued! How do you mean?

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

#318

Post by pegasus »

PeterStuer wrote: post #287
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…

"these are non-deterministic machines" Only if you choose so by allowing some degree of randomness with the temperature setting.

They are usually nondeterministic even at temperature 0 - due to things like parallelism and floating point rounding errors.

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

#319

Post by ozgung »

0points wrote: post #313

Only more mental exercises to avoid reading the writing on the wall: LLM DO NOT REASON ! THEY ARE TOKEN PREDICTION MACHINES Thank you for your attention in this matter!

Why not? What is so special about reasoning that you cannot achieve by predicting tokens aka. constructing sentences?
Post reply on HN