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

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 ]