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

341–350 of 550 posts

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

#341

Post by noobermin »

Once again, all the hypsters need to explain to me how than just programming yourself. I don't need to (re-)craft my context, it's already in my head.

pg said a few months ago on twitter that ai coding is just proof we need better abstract interfaces, perhaps, not necessarily that ai coding is the future. The "conversation is shifting from blah blah to bloo bloo" makes me suspicious that people are trying just to salvage things. The provided examples are neither convincing nor enlightening to me at all. If anything, it just provides more evidence for "just doing it yourself is easier."

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

#342

Post by phyalow »

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…

“non-deterministic machines“

Not correct. They are deterministic as long as a static seed is used.

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

#344

Post by kazga »

phyalow wrote: post #342
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…

“non-deterministic machines“ Not correct. They are deterministic as long as a static seed is used.

That's not true in practice. Floating point arithmetic is not commutative due to rounding errors, and the parallel operations introduce non-determinisn even at temperature 0.

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

#345

Post by kachapopopow »

I'll quote myself since it seems oddly familiar:

---

Forget AI "code", every single request will be processed BY AI! People aren't thinking far enough, why bother with programming at all when an AI can just do it?

It's very narrow to think that we will even need these 'programmed' applications in the future. Who needs operating systems and all that when all of it can just be AI.

In the future we don't even need hardware specifications since we can just train the AI to figure it out! Just plug inputs and outputs from a central motherboard to a memory slot.

Actually forget all that, it'll just be a magic box that takes any kind of input and spits out an output that you want!

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

#346

Post by grumple »

After a recent conversation here, I spent a few weeks using agents.

These agents are just as disappointing as what we had before. Except now I waste more time getting bad results, though I’m really impressed by how these agents manage to fuck things up.

My new way of using them is to just go back to writing all the code myself. It’s less of a headache.

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

#347

Post by quonn »

kachapopopow wrote: post #345

I'll quote myself since it seems oddly familiar: --- Forget AI "code", every single request will be processed BY AI! People aren't thinking far enough, why bother with programming at all when an AI can just do it? It's very narrow to think that we will even need these 'programmed' applications in the future. Who needs operating systems and all that when all of it can just be AI. In the future we don't even need hardw…

Is this sarcasm or not?

edit: Yes it is.

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

#348

Post by 1oooqooq »

kachapopopow wrote: post #345

I'll quote myself since it seems oddly familiar: --- Forget AI "code", every single request will be processed BY AI! People aren't thinking far enough, why bother with programming at all when an AI can just do it? It's very narrow to think that we will even need these 'programmed' applications in the future. Who needs operating systems and all that when all of it can just be AI. In the future we don't even need hardw…

why stop on what you want? plug your synapses and chemical receptors and let it also figure that out *thumbsupemoji

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

#350

Post by wiseowise »

ozgung wrote: post #333
0points wrote: post #329

Earlier quoted context omitted.

If you don't understand the difference between a LLM and yourself, then you should talk to a therapist, not me.

At least LLMs attempt to answer the question. You just avoided it without any reasoning.

Because LLMs do no reason. They reply without a thought. Parent commenter, on the other hand, knows when to not engage a bullshit argument.

Arguing with “philosophers” like you is like arguing with religious nut jobs.

Repeat after me: 1) LLM do not reason

2) Human thought is infinitely more complex than any LLM algorithm

3) If I ever try to confuse both, I go outside and touch some grass (and talk to actual humans)

Post reply on HN