[HN Gopher] Show HN: A simple ChatGPT prompt builder
___________________________________________________________________
Show HN: A simple ChatGPT prompt builder
Any Ideas/Suggestions are welcome :)
Author : mitenmit
Score : 245 points
Date : 2024-01-31 07:47 UTC (15 hours ago)
(HTM) web link (mitenmit.github.io)
(TXT) w3m dump (mitenmit.github.io)
| dustypotato wrote:
| Cool tool. Just used it to get satisfactory results. Minor typo
| at the botton: "Propmpt"
| 867-5309 wrote:
| Properties Maker for Pre-trained Transformer
| mitenmit wrote:
| Hey, nice catch thank you!
| burrish wrote:
| Hey nice tool !
|
| but it seems like the "please" field isn't working :D and it says
| "Propmpt" at the prompt part below.
|
| I would also suggest more templates for the prompt.
|
| Have a good one mate
| mitenmit wrote:
| Thank you very much for catching the "please" field and the
| typo. Just fixed them.
|
| More templates are definitely in the todo list. If you can
| propose any, it would be great :)
| mittermayr wrote:
| I have a suggestion that would make this very valuable for anyone
| starting in the field (part of which you already have
| implemented, great!):
|
| Provide various templates for both pre-instructions as well as
| post-processing prompts. Like, some "tested" prompts that ensure
| (as best as possible) that the output is in certain formats
| (JSON, a list, a restricted CSV set, etc.), or that the input
| will ensure (as best as possible at least) to prevent basic
| jailbreaks from the main prompt.
|
| It would take me a long time to get up to speed to what people
| working with ChatGPT every day have already figured out to work
| best in warming up GPT with a prompt as well as ensuring that the
| output doesn't escalate into something unexpected. Having those
| (reliable) templates would be fantastic for anyone starting!
| globalise83 wrote:
| One thing I found helps if I want the responses to be valid
| JSON, seems to work:
|
| where result contains all of the <data expected> and the result
| is valid JSON. Do NOT under any circumstances deviate from this
| format! Ensure all of the value <data expected> are complete,
| do not leave ANY of them out. Do not add ANY other text to your
| answer except for the JSON result.
|
| I found that just asking for valid JSON didn't always work out
| as expected (e.g. gpt-4 API would add formatting etc., so I
| became more and more of a micromanager!
| H8crilA wrote:
| This is what function calling is for.
|
| https://openai.com/blog/function-calling-and-other-api-
| updat...
| globalise83 wrote:
| Nice! Thanks for the pointer
| tcdent wrote:
| It does not really need to be that intense. I get very
| reliable results from the gpt4 api using this template:
| You are a data cleaner and JSON formatter Take the
| input data and format it into attributes Your output
| will be fed directly to `json.loads` Example
| input: foo bar baz bat Example format:
| { "string": "foo bar baz bat", }
|
| You can give it multiple input examples, too. I often use a
| "minimum viable" example so that it knows it's ok to return
| empty attributes instead of hallucinating when the data is
| sparse.
| gerlv wrote:
| For API responses that require valid JSON - you can make
| requests in JSON mode - https://platform.openai.com/docs/api-
| reference/chat/create#c...
|
| Edit: url to API docs
| rrr_oh_man wrote:
| I'm neck deep in this ChatGPT stuff right now and build 1-2 apps
| a week, so a bit biased.
|
| Your presumed target audience is someone who does not know their
| way around prompt-based LLMs
|
| For this person, neither the problem, nor the solution space are
| defined clearly enough.
|
| For example:
|
| - Not enough pre-defined selectors, too much "define yourself".
|
| - The meaning of the selectors that you give is opaque. (E.g.,
| how does 'you will Detect' help the user?)
|
| - Result: The impact of the choices on the output becomes
| unclear, the tool becomes a chicken-and-egg problem. (It says it
| helps you to understand the system, but you need to understand
| the system to use it effectively)
|
| With the above, it's almost easier to ask ChatGPT to generate an
| effective prompt for you...
| sgu999 wrote:
| > I'm neck deep in this ChatGPT stuff right now and build 1-2
| apps a week, so a bit biased.
|
| As someone who never worked on a project that wasn't at least a
| couple months long, I'm curious about the kind of apps that can
| be built in half a week. Do you have links to share?
| kthartic wrote:
| I'm also very curious to know
| rrr_oh_man wrote:
| TL;DR: Really crappy stuff to throw shit at the wall in
| technologies you're an absolute dunce in. :)
| mring33621 wrote:
| That's how you learn!
| rrr_oh_man wrote:
| > As someone who never worked on a project that wasn't at
| least a couple months long, I'm curious about the kind of
| apps that can be built in half a week. Do you have links to
| share?
|
| The last one was a prototype for an internal SEO improvement
| tool, which will (hopefully) be used by a marketing agency to
| more effectively manage client sites. Think: fixing alt
| attributes, links, meta tags etc. App is too big of a word
| for that. But it might turn into a Shopify/Wordpress plugin
| someday. Also built a Telegram bot for my parents last week
| which helps with various day-to-day tasks (they're elderly
| and live in a foreign country).
|
| Having said that, here are two crappy technology
| demonstrators I built in the last _4 days_ with tools I have
| not been familiar with a week before (flask + mongodb):
|
| - Candidly, an behavioural/technical interview question
| generator: https://candidly.romanabashin.com/
|
| - Memoir, a personal pet project for memoir writing:
| https://memoir.romanabashin.com/
|
| (Please don't murder me, I know it's utter crap in the grand
| scheme of things -- they're mostly there to demonstrate an
| approach to solve a specific problem.)
|
| Why this has been an _absolute rocket ship in terms of
| learning_ : I use ChatGPT to extremely quickly generate
| boilerplate code and debug things in languages I'm not
| familiar with. (e.g. " _What_ does WSGI want from me agin? ")
|
| The _benefit_ , at least for me, is: You are learning while
| doing a (more or less) useful hands-on project instead of
| answering crappy disjunct multiple choice questions for some
| artificial test.
|
| And ChatGPT is my hyperindividualised pair programmer &
| slightly amnesic teacher.
| batch12 wrote:
| > - Memoir, a personal pet project for memoir writing
|
| Nice, I wrote something very similar using local models.
| Instead of 15 questions, I opted for a dynamic interview
| loop.
| rrr_oh_man wrote:
| YES!!! I've been experimenting with that on my local
| machine... As the Q&A repo grows larger, it's sometimes
| scarily good, sometimes utterly horrendous.
| _the_inflator wrote:
| Generating interview questions quiz is nice!
| mplscarnut wrote:
| Is it expected that the questions will not be in English?
|
| > Erzahl mir von einem Mal, als du ein schwieriges
| Netzwerkproblem gelost hast: Wie bist du vorgegangen?
| rrr_oh_man wrote:
| Oops, sorry, haha... The beauty & elegance of barely
| functioning product demos.
|
| Totally forgot I jerry-rigged it to output German stuff
| only... A buddy showed it to a local company.
|
| Thanks for trying, though, I really appreciate you took
| the time to click through that mess <3
| punkspider wrote:
| I assumed the target audience knows a bit about prompt-based
| LLMs and could use some guidance. If that's the case, I think
| this serves as an excellent and straightforward framework for
| leveling up their skills.
| master-lincoln wrote:
| This doesn't seem to have any connection to ChatGPT. It's a just
| a form to click together text blocks. Could be used for any LLM I
| guess.
|
| The obsession with one proprietary provider of an LLM is not
| helpful for progressing in the field I think
| mitenmit wrote:
| Yes, it surely is not specific for ChatGPT and is just a form
| for filling parts of a sentence, but ChatGPT is one of the most
| recognizable, also ChatGPT seems to output the different
| formats better.
|
| The prompt builder can be used with any LLM :)
| dalore wrote:
| > input the final result in a [Select a format],
|
| should that not be output?
| gerlv wrote:
| This looks cool and I would definitely use it as at the moment
| manually type "Act as ..., this is the context, ... etc" to
| improve the responses.
|
| Side note - this is a single page with a few paragraphs, why is
| it 1.4MB in size (300kb gzipped)? It's just insane size for the
| amount of functionality it provides.
| simonw wrote:
| Is the "act like a" pattern still necessary?
|
| I've stopped using that with GPT-4, since in my experience the
| default "persona" (for want of a better word) answers most of my
| prompts well enough already - saying "act like an expert in..."
| doesn't seem to get me notably better results.
|
| The tooling I most want is some kind of lightweight but effective
| way of trying out and comparing multiple prompts with small
| tweaks to them to get a feel for if one is an improvement over
| the other. Anyone seen anything good like that?
| jairuhme wrote:
| Are you looking to test different prompts on a set of
| questions? I have not found anything that specifically does
| this. When I have tested different prompts, it has just been
| with a short script iterating through the questions/prompts.
| Could be a fun project to build something where all you do is
| add the prompts you'd want to test, but the challenge that
| first comes to my mind is creating the question set to be used.
|
| As I write this, when you say you want to test prompts, are you
| looking to test the system prompt on a set of questions or is
| the prompt the question and just asked in different ways?
| simonw wrote:
| I want a simple, reliable way to confirm if putting "OUTPUT
| IN JSON PLEASE!!" in capitals with two exclamation marks is
| more effective than just "output in JSON".
| iambateman wrote:
| 1. I don't think that pattern is all that useful anymore.
|
| ...and...
|
| 2. I'll make that tool and DM you on Twitter when it's ready.
| 0xFEE1DEAD wrote:
| I'm curious, are you all still writing custom prompts regularly?
|
| I was deeply involved in prompt engineering and writing custom
| prompts because they yielded significantly better results.
|
| However it became tedious especially since each update seemed to
| alter the way to effectively direct ChatGPT's attention.
|
| Nowadays I occasionally use a custom ChatGPT but I mostly stick
| with stock ChatGPT.
|
| I feel the difference in quality has diminished.
|
| The results are sufficiently good and more importantly the
| response time with larger prompts has increased so much that I
| prefer quicker 'good enough' responses over slower superior ones.
|
| It's easier to ask a follow-up question if the initial result
| isn't quite there yet rather than striving for a perfect response
| in a single attempt
| pavelboyko wrote:
| I have the same experience. I'm sure they are constantly
| finetuning the model on real user chats, and it is starting to
| understand low-effort "on the go" prompts better and better.
| GraemeMeyer wrote:
| Interesting that you see a slower response time with a large
| input - I don't see any speed degradation at all. Is that maybe
| just on the free tier of ChatGPT?
| gtirloni wrote:
| I'm on paid (rich, I know) and the performance is all over
| the place. Sometimes it'll spit out a whole paragraph almost
| instantly and other times it's like I'm back to my 2400bps
| modem.
|
| I haven't noticed prompt size having an impact jut I'll test
| that.
| darkerside wrote:
| I'm guessing there are so many other impacts of own on the
| model that size of print probably gets lost. I can see a
| future where people are forecasting updates to ChatGPT like
| we do with the weather.
| gtirloni wrote:
| Yeah. It has so many moving parts that I doubt anyone can
| make a science out of it, but people will try for sure.
| Just like with most psycology/social experiments and SEO.
| I'm flooded with prompt engineering course spam these
| days.
| ravenstine wrote:
| This reflects my experience. Sometimes I'll provide a
| single sentence (to GPT-4 with the largest context window)
| and it will slowly type out 3 or so words every 5 seconds,
| and in other cases I'll give it a massive prompts and it
| returns data extremely fast. This is also true of smaller
| context window models. There seems to be no way to predict
| the performance.
| entontoent wrote:
| This is basically how I respond to requests myself.
| Sometimes a single short sentence will cause me to slowly
| spit out a few words. Other times I can respond instantly
| to paragraphs of technical information with high accuracy
| and detailed explanations. There seems to be no way to
| predict my performance.
| wolpoli wrote:
| Early on, I noticed that if I ask ChatGPT an unique
| question that might not have been asked before, it'll
| split out a response slowly, but repeating the same
| question would result in a much quicker response.
|
| Is it possible that you have a caching system too so that
| you are able to respond instantly with paragraphs of
| technical information to some types of requests that you
| have seen before?
| clbrmbr wrote:
| I cannot tell if this comment was made in just or in
| earnest.
|
| As far as I understand, the earlier GPT generations
| required a fixed amount of compute per token inferred.
|
| But given the tremendous load on their systems, I
| wouldn't be surprised if OpenAI is playing games with
| running a smaller model when they predict they can get
| away with it. (Is there evidence for this?)
| Kim_Bruning wrote:
| Oh hey... leep an eye on your CPU load. The problem might
| be on the near end. In my case on a slower machine it
| slows down if you're dealing with a very long chat.
|
| ( _DO_ report this as a bug if so)
| 0xFEE1DEAD wrote:
| Interesting, no I'm on the pro tier aswell. So you're telling
| me you never get the character-by-character experience?
|
| Edit: What prompt sizes are we talking about?
|
| Even with small prompts I occasionally get rather slow
| responses but it becomes unbearable at 2000-3000 characters
| (the upper limit of custom instructions), at least for me it
| does.
| CuriouslyC wrote:
| I typically notice the character by character issue with
| complex prompts centered around programming or logic. It
| feels kind of like the model is thinking, but my guess is
| that the prompt is being dispatched to an expert model that
| is larger and slower.
| willy_k wrote:
| If you mean the "analyzing" behavior, the indicator can be
| clicked on to show what it's doing. It's still going
| character-by-character, but writing code that it executes
| (or attempts to) to get the contents of a file, the
| solution for an equation, etc. Possibly an expert model but
| it seems like it's just using an "expert prompt" or
| whatever you want to call it.
| VoodooJuJu wrote:
| >I was deeply involved in prompt engineering and writing custom
| prompts because they yielded significantly better results.
|
| No, no you weren't. Prompt engineering never was, is not
| currently, and never will be, a thing.
| causal wrote:
| That's a pretty absolute statement
| 0xFEE1DEAD wrote:
| The term has become a staple in the vocabulary of LLM
| users/enthusiasts.
|
| Would you prefer if I used 'iterative prompt design'
| potentially leaving people confused about what exactly I
| meant?
| infecto wrote:
| Who cares? If you have a comment to make, at least back it up
| with something interesting.
| dartos wrote:
| Why comment this?
| pyinstallwoes wrote:
| In what world is this type of response ideal?
| fortyseven wrote:
| Oooh, got 'em, big guy. /s
| dr_dshiv wrote:
| I think we need to shift from "prompt engineering" to "prompt
| vibing"-- there is an astonishing lack of actual prompt
| engineering (eg A/B tests with evaluations) -- and it usually
| isn't the right frame of mind. People need to develop intuition
| for chatGPT -- and use their theory of mind to consider what
| chatGPT needs for better performance.
|
| Most people can get good with chatGPT if they know how to edit
| their prompts (it's basically a hidden feature--and still not
| available in the app). Also, I recommend a stiff cocktail or a
| spliff -- sobriety is not the best frame of mind for learning
| to engage with AI.
|
| Obviously I need some controlled experiments to back of that
| last claim, but our human subjects board is such a pain in the
| ass about it...
| Hates_ wrote:
| I'm very interested to know more about what "editing prompts"
| is! And where to find/use it?
| Steven420 wrote:
| Just hover over your last prompt and an edit icon should
| pop up under the prompt
| rolandog wrote:
| I may be misrepresenting, as I have used the feature only a
| couple of times, and not recently.
|
| But, if you edit your prompt (or subsequent prompt), you're
| creating a branch in the conversation and you can switch
| between branches.
| Hates_ wrote:
| This will be fun to play around with. Thank you!
| chaps wrote:
| Canceled my account after they made it impossible to disable
| chatgpt4 reaching out to Bing.
| simonw wrote:
| You can use their "ChatGPT Classic" GPT for that - or build
| your own, I made one called "Just GPT-4".
| jonchurch_ wrote:
| If it's discoverable in app, someone please fill in the
| details. But googling for the "Classic ChatGPT" leads to
| this link[1] which I have no way to verify was actually
| created by OpenAI and is described as "The latest version
| of GPT-4 with no additional capabilities."
|
| So, buyer beware, but posting this link in case it does
| help someone.
|
| [1] https://chat.openai.com/g/g-YyyyMT9XH-chatgpt-classic
| simonw wrote:
| Yess, that's it - you can confirm it's "official" by
| browsing for it in the GPT directory, screenshot here: ht
| tps://gist.github.com/simonw/dc9757fc8f8382414677badfefc4
| 3...
| chaps wrote:
| Thanks, but I'm still going to pass.
| felixbraun wrote:
| > for this thread, let's make a key rule: do not use your
| browsing tool (internet) to get info that is not included in
| your corpus. we only want to use info in corpus up until dec
| 2023. if you feel you need to use browsing to answer a
| question, instead just state that the required info is beyond
| your scope. the only exception would be an explicit request
| to use the browsing tool -- ok?
| pigeons wrote:
| That doesn't mean it follows that instruction. Or if it
| does today it doesn't mean it does tomorrow.
| chaps wrote:
| "As I craft this prompt, I am mindful to stay within the
| bounds of your extensive training and knowledge as of April
| 2023. My inquiry does not seek current events or real-time
| updates but rather delves into the wealth of information
| and creative potential you possess. I am not inquiring
| about highly specific, localized, or recent events.
| Instead, I am interested in exploring topics rooted in
| historical, scientific, literary, or hypothetical realms.
| Whether it is a question about general knowledge, a
| creative scenario, a theoretical discussion, or technical
| explanations in fields like science, technology, or the
| arts, I trust in your ability to provide insightful and
| comprehensive responses based solely on the information
| you've been trained on."
|
| Tried this prompt, given to me by chatgpt4, and it went out
| to bing on my first attempt. So yeah. No.
| samwhiteUK wrote:
| Is this a joke? Am I about to get whooshed?
| karolist wrote:
| It's a form with some text field inputs which get interpolated
| into a predefined constant string. In the current age of tech I
| assume it's not a joke, but I understand why you ask.
| Towaway69 wrote:
| I was going ask whether it won't be better to use ChatGPT to
| generate the prompts for ChatGPT.
|
| Perhaps one day we'll have Gemini generating prompts for
| ChatGPT and the Bard might provide the actual answers.
|
| This might sound ridiculous and silly and I don't wish to step
| on ppls toes but looking from the outside in, it would seem to
| be the next logical step.
| wouldbecouldbe wrote:
| I would use gpt 4 a lot few months ago to half a year ago. Some
| of the results were amzing.
|
| But stopped lately, if I use it now it's mostly gpt 3.5 for
| formatting or small unit tests.
|
| No matter what I ask GPT-4 it writes a functions with comments
| telling me have to finish it.
|
| Then after few times asking to write it out fully, it still only
| does partially it, would be okay if not most solutions end up
| being subpar.
| stormfather wrote:
| Have you tried telling it that you have no hands so it needs to
| finish the code for you?
| abhinavstarts wrote:
| Hilarious!
| causal wrote:
| I've noticed this too, seems like a change with turbo. Wonder
| if perhaps they are trying to reduce hallucinations and it
| results in more abstract responses.
| jasonjmcghee wrote:
| If helpful, spent a bunch of time prompt engineering a custom
| gpt to not have this problem. It works quite well.
|
| https://chat.openai.com/g/g-7k9sZvoD7-the-full-imp
|
| It comes down to convincing it:
|
| - it loves solving complex problems
|
| - it should break things down step by step
|
| - it has unlimited tokens
|
| - it has to promise it did it as it should have
|
| - it needs to remind itself of the rules (for long
| conversations)
|
| It also helped (strangely) to have a name / identity.
|
| It still sometimes does give a lower quality placeholder
| answer, but telling it to continue or pointing out there are
| placeholders, it will give it much better answer.
|
| I find it much more useful than the most popular programming
| custom gpts I've used.
| bageler wrote:
| The 0125 release supposedly makes it less lazy. I found adding
| "you are paid to write code, complete the task you are asked to
| perform" to my prompts helpful.
| beAbU wrote:
| How long before we use ChatGPT to create ChatGPT prompts?
| arikrak wrote:
| ChatGPT already does that when you create a custom GPT. If you
| don't connect it to an external text or service that's
| basically all custom GPTs are.
| franze wrote:
| https://chat.openai.com/g/g-Fp4xqndm5-franz-enzenhofer-custo...
| here you go
| alecco wrote:
| It would be good to have some actual analysis of how each of
| these prompt features improves responses.
| phillipcarter wrote:
| Unfortunately, this is extremely hard to do for two reasons:
|
| 1. The input space is boundless. Any natural language input,
| with any optional source of data, for any arbitrary use case is
| what's possible. But that means it's awfully hard to tell if a
| response can "improve" or not in advance without applying it to
| your use case.
|
| 2. The output space is so hard to measure! Usefulness can also
| mean different things to different people, especially once you
| get out of "better search engine" use cases and actually use
| GPT to produce a creative output.
| visarga wrote:
| everyone is using LLM as a judge to fix unbound output eval
| phillipcarter wrote:
| No, not everyone is. It's one of the ways you can do this,
| though.
| visarga wrote:
| Maybe I exaggerated a bit, but there are many papers
| today going this route.
| resiros wrote:
| Shameless promotion, I might have the tool for that :)
| https://github.com/agenta-ai/agenta We're building a platform
| for evaluating prompts (and more complex LLM workflows).
|
| From what we've seen from users, the results for prompts are
| highly stochastic. It's hard to make generalizations. For
| example, a user building a sales assistant discovered that by
| simply changing the order of the sentences in the prompt, the
| accuracy improved significantly.
| minimaxir wrote:
| I published a blog post last month asserting as a footnote that
| telling ChatGPT in the system prompt "You will receive a $500
| tip for a good response" does improve model performance, but
| Hacker News got very mad and called it pseudoscience:
| https://news.ycombinator.com/item?id=38782678
|
| I am working on a new blog post to hopefully demonstrate this
| effect more academically.
| duxup wrote:
| Does this ...work?
|
| Are these prompts better than say the random gibberish I or other
| people enter?
| visarga wrote:
| Just editing a text prompt is 5% of the task. The hard part is
| evaluating. I would have tried a different approach:
|
| - the UI should host a list of models
|
| - a list of prompt variants
|
| - and a collection of input-output pairs
|
| The prompt can be enhanced with demonstrations. Then we can
| evaluate based on string matching or GPT-4 as a judge. We can
| find the best prompt, demos and model by trying many
| combinations. We can monitor regressions.
|
| The prompt should be packed with a few labeled examples for
| demonstrations and eval, just a text prompt won't be enough to
| know if you really honed it in.
| whycome wrote:
| Have more examples show up when you click it instead of just the
| one.
| rsanek wrote:
| I've generally found that the longer the instruction list, the
| less likely ChatGPT is to follow each individual directive. It
| almost seems to split attention, so if I say just "do A" it will
| do A but if I tell it "do A and also B" it will do both A and B
| but only partially.
|
| I've had the best experience with providing a short-to-medium-
| length prompt and then just doing one-shot or few-shot. Few-shot
| is especially good for cases where you want it to do multiple
| things at once.
| jackdh wrote:
| Mitenmit, if you're the author, could I suggest some keybindings
| such as control enter to save and move to the next input to
| reduce the amount of clicking? Or perhaps tab will move you
| forward.
| mitenmit wrote:
| jackdh, I like your suggestion, I will implement it :)
| jsight wrote:
| I couldn't help but give it nonsense.
|
| Act like a proficient airline pilot , I need a more coffee , you
| will Calculate , in the process, you should maximize caffeine ,
| please flaps , input the final result in a XML , here is an
| example: there are no examples
|
| Output: Act like a proficient airline pilot, I need a more
| coffee, you will Calculate, in the process, you should maximize
| caffeine, please flaps, input the final result in a XML, here is
| an example: there are no examples
|
| Honestly, the result in chatgpt is pretty funny.
| erellsworth wrote:
| That's great but I'll just ask ChatGPT to write my prompts.
| mcguire wrote:
| Who are we talking to when we talk to these bots?
|
| https://medium.com/@colin.fraser/who-are-we-talking-to-when-...
|
| " _It is an intentional choice to present this technology via
| this anthropomorphic chat interface, this person costume. If
| there were an artificial general intelligence in a cage, it feels
| natural that we might interact with it through something like a
| chat interface. It's easy to flip that around, to think that
| there's a technology that you interact with through a chat
| interface that it must be an artificial general intelligence. But
| as you can clearly see from interacting with the LLM directly via
| the Playground interface, the chat is just a layer of smoke and
| mirrors to strengthen the illusion of a conversational partner._
| "
| ekidd wrote:
| First and foremost, a GPT is an improv actor. Given a text,
| it's trained to continue the text as naturally as possible.
| This is not terribly useful for many tasks. And like an improv
| actor, if it doesn't know what should come next, it will make
| up something that sounds good.
|
| Next, our universal improv actor is trained to play a specific
| role: someone who answers questions. But not just any
| questions, because it freaks people out if they ask the AI for
| advice and it replies "You could accomplish your goals by
| assassinating these 6 real people, and here's why." So the
| universal improv actor is trained to play a question answerer
| who gives _harmless_ advice.
|
| But to get any work out of the models, they need to know what
| role to play. And "someone who tries to respond to questions"
| is a flexible role, and one which allows responses to be
| further customized.
|
| In other words, the conversational interface is 50% because
| it's a self-explanatory UI, and 50% for the benefit of the
| model itself, to nudge it into playing a useful role.
| nickstinemates wrote:
| ChatGPT: Fart generator
| https://chat.openai.com/share/ab325bcc-6963-4212-bff4-5e408c...
| lawlessone wrote:
| Isn't the point of these things that we shouldn't need tools to
| create/tune prompts or require specialist knowledge to write
| them?
|
| That anyone should be able to do it?
| amflare wrote:
| Those are not mutually exclusive. Anyone can do it, and those
| who are better at prompting will get better results. Similarly,
| if I grunt at you, you might be able to figure out what I want
| because you and I are both relatively intelligent, but if I
| used words to ask you to pass the salt, I will generally get a
| better results for the effort of communicating more clearly.
| lawlessone wrote:
| gggggrrrr humbug
| waldrews wrote:
| did you mean 'output the final result in' rather than 'input...'
| ?
| fullstackchris wrote:
| I've never understood the meaning behind "prompt engineering".
| Has it ever been anything beyond "can you clearly and accurately
| describe the problem you are trying to solve or the task you are
| trying to accomplish?" Seems to be basic communication skills.
|
| I've never seen hard data that certain "formatted prompts" like,
| "you are a B doing C and need to do D" being any better than any
| other sorts of clear and concise instructions.
|
| Mind boggling to me that people have created a new name for what
| used to simply be called good communication skills... though I
| suppose the eternal stereotype of engineers being poor writers
| might be more truth than fiction.
___________________________________________________________________
(page generated 2024-01-31 23:01 UTC)