Re:Where the Goblins Came From
by tdeck on Thursday April 30, 2026 @01:00AM
(#47958324)
Is this the "prompt engineering" that I keep hearing will be an indispensable job skill for software engineers in the AI-driven future? I had better start learning or I'll be replaced by someone who has.
[ Parent
| on HN ]
Re:Where the Goblins Came From
by heavyset_go on Thursday April 30, 2026 @01:26AM
(#47958509)
If you aren't telling your computer to ignore goblins, you're going to be left behind.
Re:Where the Goblins Came From
by qingcharles on Thursday April 30, 2026 @02:51AM
(#47959079)
I'm goblinmaxxing myself.
Is GPT5.5 goblingooning fr?
We’re definitely not escaping the permanent goblin underclass with this one.
Re:Where the Goblins Came From
by NookDavoos on Thursday April 30, 2026 @04:20AM
(#47959709)
permanent goblin underclass
I wonder how much energy OpenAI spends each day on pink elephant paradoxing goblins. A prompt like that will preoccupy the LLM with goblins on every request.
Re:Where the Goblins Came From
by HenryBemis on Thursday April 30, 2026 @02:59AM
(#47959123)
That is a great point. Machine consumes energy of adding goblins in every response. The machine consumes energy on removing goblins from every response. That is a great attack vector. If (wild imagination ensues) an adversary can do that x100 (goblins, potatoes, dragons, Lightning McQueen, etc.) they can render the machine useless/uneconomical from the standpoint of energy consumption.
In Terminator 7, everyone will carry goblin plush toys to defend themselves against the machines.
I mean probably not or they wouldn’t have shipped it, right?
Greater context size means more computational resources means more energy. Dedicating a portion of the context to telling the LLM not to refer to goblins then has a non-zero energy cost every time you prompt the model.
Prompt engineering is mostly structured thought. Can you write a lab report? Can you describe the who, what, when, where, and why of a problem and its solution?
You can get it to work with one off commands or specific instructions, but I think that will be seen as hacks, red flags, prompt smells in the long term.
If I could do those things, I wouldn't be using an LLM to write for me, now would I?
You don’t let the LLM write prise for you, you get it to translate natural language into code somewhat coherently.
Re:Where the Goblins Came From
by kilpikaarna on Thursday April 30, 2026 @03:44AM
(#47959468)
But it's much less annoying to just write the code than to try to express it in sufficiently descriptive natural language.
skill issue
Converse for me so ymmv.