Can someone tell me what the hell they use ChatGPT for? I tried it a few times and it always confidently gave me wrong results to basic things. What is this thing supposedly “disrupting”? Is it really just marketing cranking out metric tons of spam blogs?
So many things. A lot of them for personal entertainment, but increasingly for useful other stuff too.
I used it to help brainstorm talk titles and abstracts for a talk I was proposing the other day. What I ended up submitting was entirely written by me but was heavily influenced by the ChatGPT conversations.
> Can someone tell me what the hell they use ChatGPT for?
I play DnD with my friends and I’m usually the dungeon master. I use ChatGPT to help me world build, and flesh out details.
Don’t imagine asking ChatGPT what should happen in the next session. More like asking for options for the name and title of a non-player character. Then it writes options, I twist them up, combine them and select the one I like the best.
I can even ask more complicated questions like “what was so and so’s first innovation and how did it help their village? Provide 5 options” and then chatgpt goes and does that. Maybe I like one, and then that is canon from then on, or maybe while I am reading them I get an even better idea.
Basically I use it as a bicycle for my creativity. And in that use case I care 0% if what it says is true, much more that it comes up with wild things. It also doesn’t have to be totally consistent, since what it outputs is just a first step in an editing process.
For example I did know that one of the main cities in my world have grown from a sleepy village into a bustling university town because two wizzards started a friendly competition between them. And then with the help of ChatGPT I have iteratively expanded that core idea into this backstory of the city: https://docs.google.com/document/d/19dea6p9WuLcZIRVX2ecYMw8W...
I have been using it as a search replacement for most of the past month and only found two subtly wrong answers. This covers legal questions, researching product differences, wiring diagrams, suggesting books to read, correcting misremembered quotes, and about a hundred other tasks.
Of course still relying on google in the background, but increasingly rarely, and presuming all the negative commentary we've been seeing online are folk who simply haven't tested it in anger yet. Today's chatgpt hallucination is yesterday's Google blogspam etc. Folk for some reason continue to act like the old world was perfect. This is much closer to perfection than anything we ever had, and infinitely more comprehensive. Google as we knew it is already dead, because the medium google was built for just got made obsolete. This is far closer to a new Internet iteration (WAIS, FTP, Gopher, HTTP, Web2.0, ...) than it is a new search engine
Now watch as the search engines try to adapt it to their recency-biased ads model and fail miserably, as what we have is already better than what they were able to sell. Very unclear bing or Google or anyone you've heard of will win this round, its suddenly a very exciting time in tech again
Another aspect I find very exciting is that these effectively represent a return to a curation-driven Internet, selection of input data for model training is probably an interesting new form of diversification. Who cares about having a site in the world wide web if its not part of the inputs for the language models used by millions of users? That's a completely new structure for the dissemination of ideas, marketing, "SEO" etc., and a brand new form of mass media
I don't know what you've been searching for that you've only found two subtly wrong answers. It frequently gives me incorrect answers, some of which are subtle and some of which are obvious. It's given me incorrect code, told me about incorrect APIs, explained deep learning concepts incorrectly, given me wrong answers about science-related questions, made up characters wholesale when I asked it about Irish mythology, given me made-up facts about (admittedly niche) philosophers.
I'm glad you've found use out of it, but I can't imagine using it as a search replacement for my use cases.
Edit: And I don't see why it would be surprising that ChatGPT wouldn't have all of the answers. The underlying model is much, much smaller than it would take to encode all of the knowledge it was trained on. It's going to make things up a lot of the time (since it's not good at remaining silent).
Exactly my experience. And if you point out the errors, often it will correct itself (most of the time) and explain why it was incorrect before (sometimes).
I'm going to echo other people's skepticism and give a concrete example that's easy to reproduce and which has virtually no dependence on real experience in the physical world. Try asking it about public transit wayfinding trivia. Pure text matching, well defined single letter / digit service names, closed system of semantic content. All there is are services and stations and each service is wholly defined by the list of stations it stops at and each station is wholly defined by the list of services that stop at it. This should be a language models bread and butter. No complexity, no outside context, just matching lists of text together.
I talked to it about the NYC subway. Every time I nudged it with a prompt to fix a factual error or omission, it would revise something I didn't ask for and introduce new errors. It was inconsistent in astounding ways. Ask it what stations the F and A have in common twice and you'll get two wrong answers. Ask it to make a list putting services in categories, it will put the same service into more than one contradictory category. Point this out, it will remake the list and forget to include that service entirely. And that's when it isn't confidently bullshitting about which trains share track and which direction they travel.
Bullshit is worse than a lie. For a lie is the opposite of the truth and thus always uncovered. But bullshit is uncorrelated with the truth, and may thus turn out to be right, and may thus cause you to trust the word of the bullshiter far more than they deserve.
I've been spending some time trying to get a sense of how it works by exploring where it fails. When it makes a mistake, you can ask questions in a socratic method until it says the true counterpart to its mistake. It doesn't comment on noticing a discrepancy even if you try to get it to reconcile its previous answer with the corrected version that you guided it to. If you ask specifically about the discrepancy it will usually deny the discrepancy entirely or double-down on the mistake. In the cases where it eventually states the truth through this process, asking the original question that you started with will cause it to state the false version again despite obviously contradicting what it said in the immediately previous answer.
ChatGPT is immune to the socratic method. It's like it has a model of the world that was developed by processing its training data but it is unable to improve its conceptual model over the course of a conversation.
These are not the kinds of logical failures that a human would make. It may be the most naturalistic computing system we've ever seen but when pushed to its limits it does not "think" like a human at all.
> If you ask specifically about the discrepancy it will usually deny the discrepancy entirely or double-down on the mistake.
I have had the exact opposite experience. I pasted error messages from code it generated, I corrected its Latin grammar, and I pointed out contradictions in its factual statements in a variety of ways. Every time, it responded with a correction and (the same) apology.
This makes me wonder if we got different paths in an AB test.
I pasted error messages from code it generated. It kept generating the same compiler error eventually.
When I applied the "socratic method" and explained to it the answer based on stack overflow answers. It would at first pretend to understand by transforming the relevant documentation I inserted into it, but once I asked it the original question, it basically ignored all the progress and kept creating the same code with the same compiler errors.
It's a incredible at writing rich and persuasive comments that take the momentum out of bigoted Facebook posts. An extended family member is unfortunately all aboard the election fraud and "groomer" trains, posting absurd and hateful stuff constantly every day (in classic Facebook style many of these posts "do not violate the community guidelines). I and a couple other younger members of the family have taken to using ChatGPT to gently but firmly counter every lie and misdirection he tries to make. I'm not sure if it's deeply changed his mind or heart yet, but he posts much less extremist content now and has actually resumed posting wholesome and funny things like he did before going down the rabbit hole.
It’s nice to get quick in context answers to concepts and their relationships. Sometimes I have a vague notion, but with ChatGPT it resolves my hunch quite quickly without reading through a (sometimes ad spammed) article.
When I ask it for things that are obviously on stackoverflow but hard to spot or understand because they are pointlessly clever or weird, it is nigh unusable. It is a complete waste of time. Even if you paste in the stack overflow answers it will take some iterating and at that point I am teaching an unteachable AI.
I sometimes ask it "what is the standard term of art in industry which means blah?" If you google that question, you get only blogspam and people trying to sell you something, but if you ask chatgpt and then google the thing it tells you is the standard language, it's pretty easy to tell if it gave you correct info.
And then you can run searches using the standard terms, which gives better results, and also when writing code have more- informatively-named variables and better-structured data.
I have a friend who works at a large government contractor. They frequently have to respond to RFPs from the government, and had some analysts where the majority of their job was preparing responses to these RFPs.
They tried instead putting these RFPs through ChatGPT, and they were blown away by the responses they got. Of course, the responses still need to go through a thorough edit and review process, but that was also true when humans were writing the first draft.
He told me that ChatGPT obviated a couple people's jobs, with the added bonus that the turnaround time between receiving a proposal and sending a response was much faster.
The 30M figure likely includes a lot of students having ChatGPT do their homework for them. :)
I've used ChatGPT for programming aid. I've started writing some Python packages. I haven't written Python in a long time, it doesn't "flow" easily for me. ChatGPT has been helpful here for scaffolding some code.
It often gets things wrong -- but I know enough to recognize when it's gone off the rails, and then nudge it in the right direction.
A concrete example: I wanted to do an iterative breadth-first traversal of a tree. I asked ChatGPT to produce it. It produced a correct implementation, albeit a recursive one. After being reminded that I wanted an iterative version, its second attempt was the right thing.
This is a pretty small thing, I guess! But for me, it was neat to be able to specify something at a higher level and have the computer sort out the details.
> It often gets things wrong -- but I know enough to recognize when it's gone off the rails, and then nudge it in the right direction.
> specify something at a higher level and have the computer sort out the details.
Same here. I know some people frown on Github Copilot, but ChatGPT + Copilot makes a powerful combo. I actually use ChatGPT like a copilot, to talk through the structure of things, debugging issues, etc. Then Copilot works as a smarter autofill if I don't know the exact code or syntax needed off the top of my head. Both ChatGPT and Copilot get things wrong sometimes, but are correct often enough that it improves time spent. Even when ChatGPT is wrong it sometimes discusses useful concepts I had't thought about.
To be fair, I'm a self-taught and often jump between languages and frameworks that I'm not an expert in. Perhaps Copilot + ChatGPT would be less useful for a pro devs who are experts in their areas. But for my case, they're quite helpful.
Entirely separate: I also use ChatGPT to turn stream-of-consciousness thoughts into medium-length letters or emails.* Eg, I had to email a dog trainer and had a bunch of concerns to raise. It would've taken a fair number of minutes to make it coherent and easily-readable. Instead, I explained the situation to ChatGPT and hastily typed out the concerns, giving no regard to grammar, typos, or syntax. Then I asked ChatGPT to turn it into an email to the trainer with my intended tone, and it worked like a charm. That process took maybe 1/4 the time of manually writing the full email.
* this semi-stream-of-consciousness post was NOT written with ChatGPT, though perhaps it should've been
I’ve used it to write out 45 minute long lesson plans, help write complicated text message where all I’ve got is a bunch of points to make, I’ve had it correct my Portuguese since I’m not a native speaker, I’ve had it give me a baseline SQL table design to achieve a specific goal, I’ve had it come up with different ways to phrase things since I’m not creative enough, I’ve had it write marketing copy, created design briefs for my graphic design team, and on… I happily pay for it because it’s just nuts how much of a force multiplier it is for me.
Exactly! I'm doing this for German language. It is rare for translators to get correctly how people talk in German and chatGPT is astonishingly good at that task.
ChatGPT has an infinite number of uses as long as those involve text transformation in some form.
My favorite has been to feed it some slab of text and let it generate synopsis and then bullet points and then you can expand on those bullet points.
You feed it some prompts and let it expand on a topic.
My main use has been to generate multiple choice quizzes on a variety of topics for my students.
ChatGPT does a very good job 90% of a time and if some quiz is off, you just let ChatGPT make some more.
If need be you can generate code in oh about 20-30 programming languages.
Vast majority of it will be ideomatic too. Sure Copilot (which is GPT-2 or GPT-3 now?) could do some of the tasks as well but the generality of ChatGPT is astounding.
Now, it is not going to write a big application for you but ChatGPT could generate large parts of the code.
So far the only weakness (besides the rare hallucination) I've found ChatGPT tends to make up word endings in less popular human languages when translating from English. That is probably due to how tokenization is done.
Has anyone been able to have ChatGPT generate gramatically "incorrect" English?
I am talking about regular prompts (not rap or dialects).
I recently used it sort of as a rubber duck for a coding problem. I was architecting a new feature and the way I was thinking about it was a bit clunky.
ChatGPT helped point something obvious out that I had totally missed in my original problem solving.
> Can someone tell me what the hell they use ChatGPT for?
Yes, I can help explain what ChatGPT is used for. ChatGPT is a large language model developed by OpenAI that can generate human-like responses to text-based prompts. It has been trained on a vast amount of text data to understand the nuances of language and can be used for a wide range of natural language processing (NLP) tasks, such as:
1. Text generation: ChatGPT can generate new text in response to a prompt, such as writing a story, composing a poem, or generating product descriptions.
2. Language translation: ChatGPT can translate text from one language to another, making it a useful tool for language learning or communication between people who speak different languages.
3. Chatbot development: ChatGPT can be used to create chatbots that can engage in conversations with humans and provide helpful responses to their inquiries.
4. Text classification: ChatGPT can be used to classify text into categories, such as sentiment analysis, topic modeling, or identifying spam emails.
5. Question-answering: ChatGPT can be used to answer questions posed in natural language, such as providing information on a topic or answering customer support inquiries.
These are just a few examples of the many use cases for ChatGPT. It has the potential to revolutionize the way we interact with technology and make it easier for people to communicate with each other across language barriers.
I have not used it to create content for profit (yet) but have successfully used it for:
brainstorming funny/catchy slogans: not all are winners, but since it can crank out dozens almost immediately, I can pick what I like and quickly modify them in the time it takes me to think of one or two independently. As soon as I verify they aren't ripoffs of existing material, I may use one or two.
Writing poetry - it helped me to write sonnets, and further modified them to specifications. The recipients were quite impressed.
Translating existing poetry of mine into Arabic, while retaining the meaning AND rhyming in Arabic, a feat which is extremely difficult for me
Writing a business plan to my specifications that was actually useful
Writing letters to a landlord to get out of a lease
In addition, I have run my own fiction through it and had it rewrite it relatively convincingly in the styles of Lee Child, Danielle Steele, and Dashiell Hammett. That is more for fun, but I can see uses for it.
Lastly, I have attempted to use it to determine guilt in an investigation where I had already determined the guilty party, to see how close it was to replacing me. The answer it gave was wrong, but I could see that this was because of user error and it is only a matter of time.
It helps like a very low cost assistent; for instance, people complain about it writing ‘wrong code’. So do most programmers.
The confidently wrong is simply because it is not human (even though many humans do the same); it is in fact not confident; you just attribute that to it because of the language it uses. In fact, it feels nothing confident or otherwise; it just gives you crap and then you can ask it to think about it again.
Like I was asking it something and it told me the answer was 11, then it explained why the answer was 11 but at the end of the explanation it concluded the answer was 12. So I asked what it is 11 or 12; it said 12 and 11 was a mistake. Which was indeed correct. Again, that is not unlike humans at all; humans often say something with confidence and after a big of pondering, they correct themselves. Difference is, humans actually do feel confident or unsure etc.
You write and then you fine tune and fix; that is what it does. But faster and cheaper than humans. You engage in a conversation about the problem; it generates code, you check the code and tell what’s wrong, it will generate again with fixes etc. Especially with boring things like structural transformations aka a large json doc transformed to another large json doc with all kinds of operations in between, chatgpt is simply a lot faster than I would be, even with errors. Just paste a two json doc and ask typescript types and code for both to transform them one to another. Then add operations by tell on which nodes and what they should do. Ask to make jest tests.
> Can someone tell me what the hell they use ChatGPT for?
I use it like a turbo-assistant.
Can you make this <long text> more succinct?
Convert the following list into a LaTeX enumerated list. Please put a period at the end of each item.
Please convert all of the metric numbers using the siunitx package.
Convert the following into a Table using booktabs syntax.
It's really helpful in doing a lot of grunt work.
Write me a few paragraphs describing <x> (Yes. I have to check it to make sure it hasn't gone insane, but it spews workable prose for shit I don't want to write).
It's replaced about 50% of my "first touch" queries to google. Obviously coding is great (particularly if you ask it for unit tests for more complex stuff, so you can verify the code and tweak any parts it gets wrong - sometimes the nature of the unit tests tell you what Chat thinks code is supposed to be doing) - I use it a lot for writing letters/interview feedback, letters of reference, etc... I used to do interview feedback with 5 or 6 bullet points and a ranking of 1-5, and was told that we need more material - So, originally I just started doing long form writing, and groused that what I was typing was semantically identical to my original stuff - but when Chat came out I just entered the bullet points and let Chat do the long form writing for me.
The key with Chat is that you need to always validate any statements of fact (or code) - as hallucination is a pretty consistent 30% or so of the queries I send it. Google is probably used 75% of the time when I need to go double check a fact to make sure it's actually based on reality.
It gives me wrong answers for tech questions, but no more often than say stackoverflow.
Is much faster than googling or digging through blogs, gives me direct answers instead of having to dig through forums or documentation to find the piece of information I’m looking for, and there’s no ads or other garbage.
It’s become my sort of first line of defense looking for information. Imperfect but often pretty good.
It can summarise (covert freeform text to json etc), it can expand (convert these bullet points in to content) and it can transpose (rewrite this python as java).
It's a starting prompt for fiction and a research time saver for non fiction. It's a multipurpose tool. Functionally it's also a UI if you write it as hardcoded reply formats.
I'm using it for crud, i.e. generating insert sql from c++ classes. Knows how to do acid compliance it seems with multiple tables and foreign keys, saving lots of time.
It's also the better english to finnish translation than gtranslarw. Also copywriting as certain genres are highly repetitive.
* I'm learning a new programming language. "How do I do <some process> in <language>?" I get enough of an answer that I can experiment with the results.
* I have to write business emails. Instead of spending 20 minutes trying to think of the right politically correct terminology, I feed it the bullet points and it spits out a mostly proper email which I then spend another 5 minutes re-typing to get it the rest of the way.
* I've always wanted to start a blog, but I hate writing. Same idea as the previous point, but for blog posts.
I don't blindly trust it's output, but it saves me a ton of time in handling the to me bs extra stuff by filling in the edges.
The internet and books primarily focus on beginner-to-intermediate process, so there's very little resources beyond that. I've found ChatGPT to be exceptional for explaining things beyond it, like getting into more advanced Rust topics lately.
I think the key is to treat it like an experienced mentor that can make mistakes because of imperfect memory, not a perfect talking encyclopedia. Web searches don't always have the right answer, and even experts with decades of experience (cough) still get things wrong regularly. It's a collaborative conversation.
I'm using it as an extra colleague with whom I can talk about my problem, or like a very advanced rubber duck. This gets me to a solution far quicker than just researching on my own, even if its answers aren't immediately correct.
I'm using it to learn French. I'm using it for figuring out if my book idea makes sense. To tell me how Typescript works, or how it compares to languages I already know. I use it to compare products I'm interested in, to make educated guesses where comparable products are manufactured in.
It's not as smart as my colleagues, but much smarter than a rubber duck, and it has a mountain of data behind it.
It changes everything and brings amazing potential to the table.
>Can someone tell me what the hell they use ChatGPT for?
Although it's free, I pay $20 for pro version ($240 per year) plus taxes, and use it daily. I get a lot of benefits from using it.
I use it to learn about things, solve problems, suggest approaches, critique my own proposals and approaches, generate code scaffolding and smaller code solutions, help me draft emails of all kinds, etc. I find it highly useful in a variety of contexts. You can give it obfuscated impossible code and it can analyze it and tell you what it does in seconds: https://imgur.com/a/m40TR4d (someone else's result)
It can help you find bugs and mistakes in your own code.
You can also ask it to tell you about a subject and it can give you a summary. Just tell it what you want and it'll do its best.
What areas did you use it where you got wrong results for basic things, to the point where you don't find it useful? Its major limitations are around logical numeracy (it gets numbers wrong) and lack of a visual cortex, which means you can't use it for graphics code or to write you visually correct solutions. Also, it doesn't speak foreign languages perfectly, it makes some grammatical mistakes.
It mentions that it can generate a hypothesis. So a scientist can absolutely use it to make some suggestions, for example try "Generate five hypotheses a chemist might test as part of an undergraduate study program" - here are some examples: https://imgur.com/a/hOtGgKN
I'm no chemist, but those seem fine for me as undergraduate lab work tests. It's probably not going to get you a Ph.D. but often you don't need one, just a few quick brainstorming suggestions.
Some people have it plan all their meals and create recipes for them, which they then cook and eat. There are thousands of recipe sites, the reason people use ChatGPT is because they can just describe what they want, what they have, and have it come up with its own recipes based on what is available and can be purchased.
Just describe what you need and what you want it to do and it does a good job for you on all sorts of tasks.
Using Jobs famous words you are using it wrong. ChatGpt is more of a writing tool rather than an information tool. It helps you to write stuff the information it writes does not need to be accurate
I had a conversation with it in Latin yesterday. I also just spent way more time than I care to admit on inquiries about late-18th/early-19th century governments. It seems better at providing high-level information than specifics. I consistently find errors in anything to do with dates or calculations, but it is accurate enough to be very useful to me. Much better than the vast majority of my elementary school teachers, at least.
Slightly out of left field - I'm using it to generate Chinese conversations for foreign language students, paired with TTS voices and 3D avatars, streaming live on Twitch.
GPT is not just about text it’s about language, that fundamentally human thing. It’s not AGI but it’s moderately close for a whole huge range of use cases. So it’s a great product, but it’s not a new being.. in the sense we are—sorry ChatGPT! no offense to your brilliance, just sayin’.
Can you give examples about what and how you asked and what it said?
BTW How you ask is the lion’s share of making it useful to you
There’s a community plugin for obsidian note taking which takes openai api key and let’s you write notes with help of chatgpt
For eg, I like to scribble things
And then ask gpt model to generate an outline, summarize something, make it more impactful, sound authoritative etc. this does help me sound better since English is my second language but I do verify the output.
Another example: it's really good at identifying idioms/turn of phrases.
You just ask it: provide a list of idioms/turn of phrases equivalent to <this situation>
And it will give you everything it knows about. It's great for exactly these types of queries which are hard to google (if you try, you just get blogspam)
I also don't find it particularly disruptive, but it's a nice interface to search for synonyms / ways to rephrase stuff, much preferable to googling (which is more of a failure on Google's part than anything).
Also, ChatGPT writes simple unit tests and SQL queries very well.
The only actually useful thing I found for myself so far, was as a helper for TTRPGs. Essentially a random story (encounter, issues, background, anything) generator on steroids.
I asked it to act as CEO, PO, UI designer and programmer gave it goal and asked to pursue goal by asking itself next question until it solves problem. This is fun.
I use it to generate and troubleshoot SQL queries. I work as a PM so the queries can be ineffective in terms of performance and scale as I just need the results.
I used it to successfully write a job posting for a few engineering positions. Those things are 90% fluff anyway. The prompt was something like:
>Write a job listing for a front end engineer with 3 years in vue and mention some bullshit about how innovative $company_name is and how great it is to work a $company_name.
Two pages of corporatese and got a bunch of good responses.
