[HN Gopher] Ask HN: How did ChatGPT4 blew your mind lately?
       ___________________________________________________________________
        
       Ask HN: How did ChatGPT4 blew your mind lately?
        
       What's the last time that ChatGPT4 blew your mind with its
       response?
        
       Author : endorphine
       Score  : 25 points
       Date   : 2023-05-06 15:13 UTC (7 hours ago)
        
       | demarq wrote:
       | It's ability to debug IS UNPARALLELED!
        
       | subjectsigma wrote:
       | This week between ChatGPT and Phind I asked an AI four questions.
       | Two were about SMT-LIB, one was about homomorphic encryption, and
       | one was about software-defined networking.
       | 
       | Both ChatGPT and Phind insisted on giving me example SMT problems
       | and then incorrect solutions to them. The HE answer was so vague
       | as to be useless, and I don't actually know enough about SDN to
       | verify the last one but it _seemed_ useful.
       | 
       | Overall it didn't give me a lot of confidence in the two systems.
        
       | smoldesu wrote:
       | Honestly, it hasn't. Last night I was trying to use it/Bing to
       | write a simple API request based on a JSON schema, and it failed
       | miserably. Nothing super complicated either, it was just a poor
       | fit. Both GPT3 and GPT4 repeatedly generated nonworking code,
       | which surprised (and frustrated) me.
        
         | jstarfish wrote:
         | I've had astoundingly inconsistent results myself.
         | 
         | Sometimes it'll write really elegant code that just nails the
         | request. Other times it insists the task is impossible ("too
         | complex"). Days later it'll do it without fuss.
         | 
         | I suspect there's some sort of model shell game going on behind
         | the scenes. The best results I get are _always_ outside of
         | business hours.
        
           | ftxbro wrote:
           | > Other times it insists the task is impossible ("too
           | complex").
           | 
           | This is the lobotomization. It's interesting to watch the
           | interviews with some red teamers and bing integration devs
           | who had access before they did this to it. They are fully
           | Blake Lemoine'd.
        
       | ian0 wrote:
       | I asked it to draft a legal document based on some bullet points
       | and it created it, in a different language, in keeping with the
       | legal norms of that country. I sent it to a local lawyer for
       | review and they only came back with very minor things.
       | 
       | Did the reverse with some regulatory documents too, asking it to
       | summarise in vernacular then asking specific questions to better
       | wrap my head around the docs. I wouldn't trust it fully for this
       | of course, more like a supplementary learning aid.
       | 
       | I keep hitting limits with context size though. Eg. When coding
       | it becomes cumbersome once your project hits a certain
       | complexity. You have to carefully construct prompts to get useful
       | outputs. Being able to add the entire source code into a prompt
       | to have more contextual responses would really increase utility.
        
         | mk89 wrote:
         | Out of curiosity, are you able to disclose the very minor
         | things? You don't have to use the real terms etc., anonymised
         | are good enough :)
        
       | theRealMe wrote:
       | Idk about "blow my mind" but I was surprised that it helped me
       | figure out "the song at sporting events that goes "boom boom,
       | ch"."
       | 
       | Maybe that's an easy thing to know, but I expected to not get a
       | good answer.
        
       | roschdal wrote:
       | ChatLGBT is still stuck in 2021, so humanity still has two years
       | competitive advantage.
        
       | noud wrote:
       | ChatGPT4 blew my mind when I asked it some specific details about
       | my PhD thesis. It was a relative simple question, but you needed
       | to know some domain knowledge to give the correct answer. ChatGPT
       | not only gave a wrong answer, it completely made up a story was
       | beyond repair. It is concerning (blew my mind) how confident
       | ChatGPT can provide a completely wrong answer.
        
         | ithkuil wrote:
         | Have you pasted (parts of) your thesis as context?
        
         | was_a_dev wrote:
         | Interestingly, I asked about my field of research it just
         | outputed a combination of the two open-access review papers for
         | the field.
         | 
         | It was nothing special, nor not completely correct, but it is
         | the first time I've been able to pinpoint ChatGPTs source.
        
           | kevviiinn wrote:
           | GPT4 seems to do a better job with not making up references
           | than GPT3.5. Don't check the DOIs though
        
             | was_a_dev wrote:
             | Are those references just relevant sources, or actual
             | citations?
             | 
             | For my example I knew of the sources already. ChatGPT
             | didn't make the connection
        
               | kevviiinn wrote:
               | Sometimes either just relevant or actual citations, I've
               | seen both. If you ask for specific citations for a
               | specific phrase it's basically a coin flip what you get,
               | what you get could be fake citations
        
         | mensetmanusman wrote:
         | A recent thesis is a single datapoint at the edge of human
         | knowledge. These bots will necessarily be better at parsing
         | information with more interconnectedness closer to the core of
         | existing human knowledge.
        
       | themoonisachees wrote:
       | I've been automating some of our team's most menial tasks and
       | since we're in a corporate environment we don't have control over
       | what is and isn't installed on our servers, so using bash is the
       | sane default choice.
       | 
       | None of the scripts it produced are incredible or whatever (the
       | tasks being more menial than lohic-based), but considering the
       | intricacies of bash and how often I just faceplant into them as
       | an experienced sysadmin, if feel as though the ability to just
       | say "write a script that compares a list of agents against every
       | manager and outputs the ones not found anywhere" and have it
       | output basically a working script first try is impressive.
        
       | akasakahakada wrote:
       | Got a novel idea about some math and GPT4 give me legit advices
       | and implications.
        
       | micahscopes wrote:
       | I recently used it (in combination with copilot) to implement
       | weighted, blended, order-independent transparency for a network
       | visualization project I'm working on... in just one long evening.
       | 
       | Only to realize in the process that all I really needed was to
       | modify the shader program's blend mode. Never in my wildest
       | imagination a year ago would I even dream of implementing WBOIT
       | in one night and then just leaving it in a branch.
       | 
       | In the process I also came up with a little trick on my own,
       | using what I learned, of modifying the depth values a bit in my
       | fragment shader in a way that let me selectively blend/occlude
       | stuff.
        
       | mike_hearn wrote:
       | As a side project I've been writing a tool that drives GPT4 for
       | coding purposes. It finds FIXME comments and equips the LLM with
       | a set of high level shell commands it can use to explore the
       | codebase and edit the files. This works well and I find it
       | superior to the (often semi-broken) chat UI that OpenAI provide.
       | There's no need for copy paste, and it can be given instructions
       | like                   // FIXME: Implement this class paying
       | attention to the unit tests
       | 
       | at which point it will go look up the unit test class, read it,
       | understand what the code needs to do and proceed to edit the
       | necessary algorithms into the code. The tool is a mix of response
       | parsing/execution and prompt building, so it can do
       | builds/tests/fix cycles. At the end you get a git branch with the
       | work it's done.
       | 
       | By this point I'm kinda developing an intuition for what GPT4 can
       | and can't do, but whilst pushing against what it _can_ do I still
       | often find myself being impressed. Maybe not  "mind blown"
       | anymore because it's amazing how quickly you can get used to this
       | stuff, but still. Not only does it do an excellent job of
       | figuring out what to do when the instructions are clear enough,
       | but it also has commands for adding library dependencies and will
       | use relevant open source libs to make its job easier.
       | 
       | The hard part about using this sort of tool is that you can
       | quickly become bottlenecked on figuring out what it is you
       | actually want. It's easy to run ahead of yourself and end up with
       | a mess. This sort of very rapid "painting with code" feel is a
       | bit new; probably the slowness of typing allows your subconscious
       | to think ahead a bit when doing programming normally. Also, I'm
       | still teaching it how to explore the codebase efficiently so
       | things that require a lot of context aren't quite there yet. I've
       | got a whole plan for how to make that work better though.
       | 
       | I expect at some point soon some big company or some $100M "seed
       | round" startup will come along and do this better, but I didn't
       | want to wait.
        
       | pcdoodle wrote:
       | That i'm finally breaking my "just google it" habits for
       | technical stuff.
       | 
       | Had it write non blocking micro-controller code for a project
       | (about 75% of the output was put into production) it helped
       | making variable names and general structure. The first output was
       | bad because it blocked the button read while "breathing" and led
       | but then I told it: "non blocking code please".
        
       | lukevp wrote:
       | I see a lot of replies here talking about asking GPT questions in
       | a domain an individual is an expert in, and being disappointed in
       | the results. I think this is missing the point a bit. The
       | impressive part of GPT isn't that it's an expert in anything, but
       | that it's better than an average human on many topics. For
       | example - someone brought up GPT not comprehending homomorphic
       | encryption fully. Well, I have a MS in CS and have been
       | professionally developing software for 15 years, and I've even
       | READ articles on homomorphic encryption multiple times, but I
       | can't articulate what it is very well. I just remember it's
       | inefficient and infeasible at this time.
       | 
       | The thing that is mind blowing to me is that I can talk with GPT
       | about basically any topic and it can help get me in the right
       | direction, I can talk with it to get clarity on anything that's
       | confusing, and it's like a way to collaborate on thought without
       | a human. That's mindblowing to me!
        
         | bradgessler wrote:
         | I describe GPT as _really_ good at bridging contexts. As you
         | point out, it does a great job pointing you in the right
         | direction on pretty much any topic. I was using it with my 7 yo
         | daughter and asked it to explain calculus in a way a 7 yo could
         | understand and it did a pretty good job.
        
           | was_a_dev wrote:
           | I agree. I use it in research to discover solutions or fields
           | I wasn't even aware that exist
           | 
           | Once discovered, I can go search more conventionally for more
           | reputable sources
        
         | Waterluvian wrote:
         | If ChatGPT is impressive when discussing any subject, unless
         | you're an expert, it should be a journalist.
         | 
         | Okay, I know that sounds like a sleight but I mean it in
         | reverse: we give it a hard time for failing at something humans
         | can't do either: be an expert at everything. Journalists do a
         | great job despite regularly driving SMEs nuts.
         | 
         | I use it not for querying immutable truths but for exploring
         | topics. It trivializes what used to be paralyzing for me:
         | "where do I begin if I want to learn about X?"
        
       ___________________________________________________________________
       (page generated 2023-05-06 23:02 UTC)