Hacker News Reader

I disagree. The LLM outputs really do lack anything original or interesting. They just produce banal copy whatever you ask them.

A good editor could probably reduce all LLM outputs on a subject down to the same point.

> They just produce banal copy whatever you ask them.

Nope, if you provide pages and pages of example of a style to imitate, it will do it and do it fairly well. Of course how well they do it differs from one model to the next, but providing context and extensive system prompt does change things every time.

Imitation is banal.

Yes but not very different results (unless you're adding new information to your prompt or reducing some ambiguity). Prompt engineering is mostly pseudoscience.

What we need is steering so that we can have models with different personalities, not just different prompts (because context is subject to forgetting), but this will never happen with closed-weight models, I'm not sure if it's even feasible at scale.

Yet another reason why the future is open weight.

> Prompt engineering is mostly pseudoscience.

Not my experience.

Do you have anything others can reliably reproduce? If not… well it wasn't science.

A controller has to be at least as complex as what it is supposed to control.