News for hackers. Stuff that matters.

A comment on The new skill in AI is not prompting, it's context engineering. Parent comment

Re:The new skill in AI is not prompting, it's context engine... by Aeolun on Tuesday July 01, 2025 @06:44AM (#44432520)
> Why are we drawing a difference between "prompt" and "context" exactly?

Because they’re different things? The prompt doesn’t dynamically change. The context changes all the time.

I’ll admit that you can just call it all ‘context’ or ‘prompt’ if you want, because it’s essentially a large chunk of text. But it’s convenient to be able to distinguish between the two so you can talk about the same thing.

[ Parent | on HN ]
Re:The new skill in AI is not prompting, it's context engine... by __loam on Tuesday July 01, 2025 @07:41AM (#44432897)
It's all the same blob of text in the api call
[ Parent | on HN ]
Re:The new skill in AI is not prompting, it's context engine... by FeepingCreature on Tuesday July 01, 2025 @08:40AM (#44433343)
There's always been a distinction between prompt and data.
[ Parent | on HN ]
Re:The new skill in AI is not prompting, it's context engine... by simonw on Tuesday July 01, 2025 @09:09AM (#44433557)
LLM's can't distinguish between instruction prompts and data prompts - that's why prompt injection attacks exist.
[ Parent | on HN ]
Re:The new skill in AI is not prompting, it's context engine... by FeepingCreature on Thursday July 03, 2025 @07:25AM (#44453881)
I agree, and that's a problem. It doesn't mean the distinction doesn't exist, in fact it shows the opposite.
[ Parent | on HN ]
Re:The new skill in AI is not prompting, it's context engine... by oblio on Tuesday July 01, 2025 @08:53AM (#44433432)
Spoken like a non Lisp programmer.
[ Parent | on HN ]
Re:The new skill in AI is not prompting, it's context engine... by chestervonwinch on Tuesday July 01, 2025 @08:52AM (#44433425)
There is a conceptual difference between a blob of text drafted by a person and a dynamically generated blob of text initiated by a human, generated through multiple LLM calls that pull in information from targeted resources. Perhaps "dynamically generated prompts" is more fitting than "context", but nevertheless, there is a difference to be teased out, whatever the jargon we decide to use.
[ Parent | on HN ]