You’re at least 18 months out of date claiming that prompting will be the new hot skill. Turns out LLMs are also good at prompting other LLMs.

▲ jltsiren 5 minutes ago | parent | next [-]

One of the key skills of a professor is asking the right questions. Figuring out something worth working on, and then framing it in an appropriate way and asking questions that allow someone with specific tools and skills to make progress in the topic. Usually the tools and skills are those available to a new student, but working with an LLM is similar.

That skill comes with experience. Most people don't have it immediately after PhD.

▲ throwup238 3 hours ago | parent | prev | next [-]

Calling it prompt engineer is doing it a disservice. With agents we’re well into process engineering, which is a ton more interesting.

The obvious baby’s first process is “plan -> execute” but as we learn about the strengths and weaknesses of LLMs you have to start unpacking that process into planning, prototyping, testing, validation, reviews, and tons of research. If you treat it like an extension of your brain that can automate some thought processes, it becomes a lot more powerful.

▲ brookst 3 hours ago | parent | prev | next [-]

Ah, but who prompts the prompters?

▲ jdw64 3 hours ago | parent | prev | next [-]

I find it strange that people sometimes think of knowledge as 'public property for everyone.' The essence may be one, but the mental model of knowledge is individual. For an LLM's knowledge to become mine, I need to digest it to some extent.

And programming, as the programmer who created Eliza once said, is the act of becoming a legislator of your own universe. So even if there are black boxes, if you want to build a program that fits your own worldview, studying is essential.

▲ jdw64 3 hours ago | parent | prev | next [-]

Rather than prompt engineering, I think it should be called overall harness engineering. Anyway, that's how I feel these days

	▲	skeledrew an hour ago \| parent [-]
		I think harness engineering is more broad, including not only the - system - prompt but also tools and skills made available to the LLM.

▲ cromka 3 hours ago | parent | prev | next [-]

That doesn't make any sense; you can't have one LLM to read your mind to prompt another LLM.

▲ semiquaver 2 hours ago | parent | next [-]

  > you can't have one LLM to read your mind to prompt another LLM

I’m excited to inform you that we as a species have developed a particularly useful facility known as Language which these LLM tools are evidently rather handy at wielding. This facility is particularly useful in this context when it takes the form of “dialog” or “questioning”, which can be used to propagate abstract ideas by means of mutually-feedback-guided-iterative-Language-use-turns, or more concisely, “conversation.”

One might even say that this remarkable facility can be used to “read” the ideas from one entity’s mind, such that after sufficient dialog the second entity obtains a (possibly lossy, but there are mitigations for this) copy of the ideas of the first. You might further be surprised to learn that this sort of idea-transfer business using language has already been happening in our society and species for quite some time indeed.

	▲	skeledrew an hour ago \| parent \| next [-]
		Made my day XD
	▲	pessimizer an hour ago \| parent \| prev \| next [-]
		This is a lot of words to say that a human can prompt an LLM to tell it what they want. edit: it reminds me of all that I have to wade through after I've asked an LLM a straightforward question and the answer should have been "yes, you're right."
	▲	thmoonbus an hour ago \| parent \| prev \| next [-]
		so, promoting?
	▲	cromka an hour ago \| parent \| prev [-]
		You mean promoting, right? Did you read the thread?

▲ sigbottle 3 hours ago | parent | prev | next [-]

I'm going to keep on repeating this on HN threads until I'm blue in the face, but:

There are two ways to solve a problem. Either solve the problem, or deem it irrelevant.

The implication here is that, you, the human operator, clearly are just confused. The LLM knows best. You're just a stupid human. The LLM knows objective truth, you do not. You have concerns, questions, the LLM didn't understand your question "properly"? Do not worry, the LLM objectively knows the optimal course of action. It thought through the implications of what you said, took into account all possible data, and came to the objectively correct design for your software, your society, your life.

In some sense, this problem would have been a societal problem within the next several decades anyways, but it's been hyper-accelerated by AI.

▲ xg15 3 hours ago | parent | prev [-]

Waiting for the next Neuralink announcement...

	▲	cromka an hour ago \| parent [-]
		That's still prompting, just justing a different interface.

▲ aprilthird2021 3 hours ago | parent | prev [-]

And yet in this case a human prompted the LLM for this result, not another LLM