News for hackers. Stuff that matters.
Re:Stop Building AI Agents by troupo on Thursday July 03, 2025 @01:55AM (#44452051)
> knowing how the models behave, simply providing more/better context and instructions can fill this gap

No.

--- start quote ---

prompt engineering is nothing but an attempt to reverse-engineer a non-deterministic black box for which any of the parameters below are unknown:

- training set

- weights

- constraints on the model

- layers between you and the model that transform both your input and the model's output that can change at any time

- availability of compute for your specific query

- and definitely some more details I haven't thought of

https://dmitriid.com/prompting-llms-is-not-engineering

--- end quote ---

Re:Stop Building AI Agents by A4ET8a8uTh0_v2 on Thursday July 03, 2025 @07:24AM (#44453872)
I think you are being unfairly downvoted as you raise a valid point. The real question is whether 'prompt engineering' has an edge over 'human resource management' ( as this is the obvious end goal here ). At this time, the answer is relatively simple, but I am not certain it will remain so.