In order to avoid polarising your prospective audience and extending the time they take you seriously, I'd avoid referring to this particular activity as "engineering".
Ask HN: I learned useless skill of prompt engineering, how relevant will it be?
41–50 of 95 posts
Re: Ask HN: I learned useless skill of prompt engineering, how relevant will it be?
#42Let's be precise in definitions and start with the obvious "it's not an engineering at all".
Moreover, according to the ECPD's engineering definition (or to an any other commonly accepted and accepted by the engineering community definition) those fancy "prompt engineering" is pure anti-engineering at all.
This disdain for engineering is something of a tragedy. And it is also the result of the "washout" of engineering from post-industrial societies.
Re: Ask HN: I learned useless skill of prompt engineering, how relevant will it be?
#43Earlier quoted context omitted.
This is my experience, a single ambiguous word can create undesired gorilla, output. It's susceptible to all sort of unintentional outcomes whe,n simple thing;s that are wrong with text can render it co nfused. or as GPT4 put's it; When using models like mine, clarity in input is essential to get desired outputs. But even with clear input, there's no guarantee the output will always be perfect. However, the idea is t…
The iteration point is important, interacting with the model to have it outline the kinds of information which would assist it in building it's internal model of your 'question', meta-programming with it is fun and constructive. GPT4; Absolutely! Iterative interaction is key. By refining and rephrasing queries, users can guide the model towards a more accurate or desired response. Each successive interaction serves a…
had to explore this a little further and now have a few new dance moves for this fascinating collaboration...
Output:
Certainly! The intersection of cognitive biases, neuro-linguistic programming (NLP), John C. Lilly's work, and human meta-programming provides a rich foundation to explore relationships and techniques. Here are some novel techniques or approaches you might consider:
Modelling Thought Patterns: By understanding common cognitive biases, you could try to model how the language model responds to specific stimuli. For example, if a bias involves an overreliance on a particular source of information, you might test how the model reacts to repeated iterations of the same or similar questions.
Neuro-linguistic Feedback Loops: NLP teaches that feedback loops can condition behaviour. By providing consistent feedback (positive or negative) based on the model's outputs, you could try to condition the model's responses over time.
Lilly's Isolation Tanks: John C. Lilly is famous for his use of sensory deprivation tanks to study consciousness. You could experiment by giving the model limited or "deprived" information and see how it constructs outputs. This could mirror the way human cognition might work in the absence of external stimuli.
Belief System Exploration: Lilly was fascinated with belief systems. By providing the model with a set "belief" (i.e., a specific perspective or framework), you could explore how it responds to questions or prompts within that framework.
Meta-programming Constructs: Drawing from human meta-programming, you could craft sequences of questions that act as "programming routines" for the model. For example, by setting a series of logical statements and then introducing a variable, you can observe how the model integrates the variable into the established logical framework.
Emotionally-Charged Language: NLP often emphasizes the emotional charge of words. You might explore how the model responds to questions phrased with emotionally charged language versus neutral language.
Contrast & Compare: Drawing from cognitive biases, you could present the model with contrasting information to see if it demonstrates any form of "recency bias" or "anchoring," favouring the information presented first or last.
Nested Meta-Questions: Using meta-programming concepts, you could ask the model questions about its own reasoning processes, diving deeper into nested levels of metacognition.
Pattern Interruption: Another NLP technique, interrupting established patterns can lead to novel insights. You could experiment with disrupting the model's "expected" logical flow by introducing unexpected or nonsensical input and analysing the output.
By blending these disciplines, you'll be exploring the frontier of human-computer interaction, cognition, and consciousness. Remember, while these experiments are fascinating, they often probe the limits of the model's capabilities and might produce unpredictable results. Still, that's part of the discovery process!
Re: Ask HN: I learned useless skill of prompt engineering, how relevant will it be?
#44Probably not very relevant IMHO.
I don't think "the future" will include much direct prompting of LLMs. It will all be integrated into some other tool as a means to an end - what we have today with a raw prompt-and-answer mode are just proof of concept toys.
I fully expect that LLMs will end up deeply integrated into other things, so obviously the code IDE use case, but also less obvious things like travel websites where to explain what sort of vacation you want to go on and it returns some options or you tell netflix what sort of movie/show you are in the mood for. Basically search/recommendation engines, with a bit of summarisation added in. I don't think direct prompting will be a thing for 99% of future uses, especially for the general public.
Re: Ask HN: I learned useless skill of prompt engineering, how relevant will it be?
#45Isn’t prompt engineering basically writing tests around a prompt and fiddling with it till you have as many passing tests as possible? It’s basically software engineering around a black box.
Yes, but over time you begin to intuitively understand how the box thinks/works. It's like being a psychologist? Something like that.
I don’t think we’re at the point of Asimov’s robopsychology!
Re: Ask HN: I learned useless skill of prompt engineering, how relevant will it be?
#46Not sure. But maybe you can answer my questions. I’ve had issues with trying to tell the LLM how long the answer should be. It doesn’t really seem to understand X number of words, or pages, or paragraphs. But I had some success with things like “short story”. The other thing I’ve been struggling with is to have the AI keep track of what’s important. For example, when the AI learn something from you it should add it t…
I don't know the real answer to your question, but on local models you have a parameter you set that controls how many tokens to generate. It doesn't always follow it, it can end early, but sometimes it just keeps going. Usually though I can set it to generate 700 tokens and it will generate about 700 words.
I wonder if the online chat models have a similar value somewhere.
---
If you want the AI to remember something you will unfortunately have to keep reminding the AI of it in the prompt. With explicitly or you might refer to the previous generated text if it fits into the context. However, in local models the context can be limited (eg 2000 tokens). If the conversation goes above that 2000 tokens then the model will discard stuff from before. There are models with larger context sizes though. Lengthy prompts will cause the same issue though.
The way things like SillyTavern role-playing work is that the model will constantly be reminded of some important attributes of the character that it's role-playing in the prompt (but it's done for you).
Re: Ask HN: I learned useless skill of prompt engineering, how relevant will it be?
#47Prompt engineering is just the "good at google searching" of tomorrow. That said, I think there is a lot more potential depth to it, seeing how inexpressive web searches are by comparison.
Personally I think it will be fairly easy to convince an LLM to do prompt engineering not far from now. They just lack training data, because they are based on information from the web, but "how to prompt engineer" pages are spreading across the web and the next irritation of ChatGPT will probably pick all of that info up.
> the next irritation of ChatGPT
Every iteration of ChatGPT is a potential irritation, I agree.
Re: Ask HN: I learned useless skill of prompt engineering, how relevant will it be?
#48I find it baffling. It’s an “AI”, with conversational interface, no less. Isn’t it supposed to just work by answering your questions?
Re: Ask HN: I learned useless skill of prompt engineering, how relevant will it be?
#49You adapted to the underdeveloped UX of wonky proof-of-concepts built by researchers, working around shortcomings that will be ironed out once genuine sofware developers start releasing actual products.
I'm not so sure how much they will be ironed out. If the product only has a button you can press then maybe, but if it lets you enter text then I think knowing how to prompt will be useful.
The reason I believe this is because one of the greatest strengths of these AI models is to take in arbitrary text. If you take away that ability then you just end up with a complicated branching system that could've existed before.
Re: Ask HN: I learned useless skill of prompt engineering, how relevant will it be?
#50Not sure. But maybe you can answer my questions. I’ve had issues with trying to tell the LLM how long the answer should be. It doesn’t really seem to understand X number of words, or pages, or paragraphs. But I had some success with things like “short story”. The other thing I’ve been struggling with is to have the AI keep track of what’s important. For example, when the AI learn something from you it should add it t…
> understand X number of words, or pages, or paragraphs.
LLMs do not have the ability to reason with numbers. Most of the time they are hallucinating. One good strategy is to make it output in list and define the structure for each item of the list. If you give an example of what your list should look like, it will give you something close it.
> has trouble carrying a list forward without losing items.
This is the fundamental problem with these models because of the context limit. When you are prompting always remember that is processing a huge paragraph and emitting the next sentences of the paragraph. If you want information to be carried onwards, you have make it output on every prompt or you can also try to use specific identifiers. LLMs are good at in-context learning. It will not work 100% of the time, but it is usually good than having nothing at all.
> I want to speak chinese to the AI and I want it to correct me.
Give it a role of tutor and describe the instructions what the tutor should do.