Tell HN: Copying and pasting from ChatGPT unsolicited sucks

Today at least, to me it feels like sarcasm is the root of the human behavior motivating this.

Ah netiquette! Haven’t heard that term since 90s in a Dummies Guide to the internet!

Actually, yes. ChatGPT is a tool, like google search engine. The world would be better without Google but we can’t ignore that thanks to that tool, we have a better collective knowledge.

I'm probably in the minority, but I prefer C-f through a FAQ rather than writing with a chatbot, trying to explain what I'm looking for.

It probably doesn't help that most of the current chatbots suck like hell (ehlo bank & insurance).

If ChatGPT responses were reliably correct this would be true. Otherwise it’s just going to cause more confusion.

Nice. I feel like BBS star scans better.

Ruin it?

While ChatGPT comments may not offer much in terms of original thought, it's important to remember that they are generated by a machine learning model and should not be held to the same standards as a human's response. It's unfair to accuse someone of posting a ChatGPT generated comment without proof, as doing so can lead to unnecessary conflicts and misunderstandings. It's always best to give others the benefit of the doubt and assume that they are contributing to the conversation in good faith. It's also important to remember that it's okay to disagree with someone or to challenge their ideas, but it should always be done in a respectful manner.

-

On a more serious note, I've seen some downright jarring comments come out of ChatGPT that honestly give me the impression that original thought isn't as original as I want it to be...

My new pasttime is pasting things from here in and seeing the results: https://old.reddit.com/r/AmItheAsshole/

It managed to call out someone for weaponizing identity politics at one point, that's a level of thought a step above "Showing me google results for what I typed in with extra spice" that GPT3 tended to result in

this is obviously chatgpt content pasted as a joke. if not you write in the same tone.

Both emojis and excessive gif meme usage didn’t go away if I see insta, TikTok and often Twitter.

That was my only response to this post, seriously, he's begging to be trolled...

I am glad I am not the only one who hasn't gotten past the phone number barrier.

Now if ChatGPT had written that response I would be impressed!

FYI, it wouldn't take my Gvoice number (natch) but it does accept Flowroute DID numbers. This was what finally made me get around to figuring out how to accept SMS over callback/webhook/whatever it is (instead of paying however much FlowSMS is charging now). I can share nginx config if anyone is trying to do the same

  load_module "/usr/lib/nginx/modules/ngx_http_echo_module.so";
  http {
    log_format postdata $request_body;
  }

  server {
    location /numbers/1NPANXXxxxx/relationships/sms_dlr_callback {
      access_log /var/log/nginx/example.com/postdata.log postdata;
      echo_read_request_body;
      }
    }

Here's what actual response to his post, fully cited, from ChatGPT would be:

It is not helpful for Person B to simply paste the response of a language model without providing any additional context or explanation. By doing so, Person B is not contributing to the conversation and is not providing any value to the discussion. Additionally, this behavior can be confusing and misleading for other readers who may not be aware that the response is from a language model and not from a real person. It is important for all participants in a conversation to contribute their own thoughts and ideas in order to have a productive and meaningful discussion.

offer a suggestion

One suggestion for Person B could be to provide their own thoughts and ideas in response to the question, rather than simply pasting the response of a language model. Person B could also provide some context or explanation for the response of the language model, to help other readers understand the relevance of the response and how it relates to the original question. Additionally, Person B could engage with the other participants in the conversation and ask follow-up questions or provide additional insights to further the discussion. By actively participating in the conversation and providing value through their own contributions, Person B can help make the conversation more productive and enjoyable for everyone involved.

how would we enforce that?

Enforcing the suggestion for Person B to provide their own thoughts and ideas in a conversation would be difficult to do in practice. One potential way to encourage this behavior would be for the community to establish norms and expectations around participation in discussions, and to provide positive reinforcement for those who contribute meaningfully to the conversation. For example, other participants in the conversation could provide feedback and recognition to those who contribute their own ideas and insights, and could avoid engaging with those who simply paste responses from language models without providing any additional value. Over time, this could help to establish a culture of active and meaningful participation in discussions, and could discourage the use of language models as a substitute for real human engagement.

effectively, ChatGPT is advising us to use voting.

It looks like I have Internet Connectivity issues!

I tried to ask it earlier, and it wanted to confirm my phone number. I do not have my phone in the office

I can smell a bot

ai wrote this ^

There should be a permaban from HN for using LLMs or other AI to write comments, as they provide no useful, authentic discourse.

Yeah, chatgpt becomes less impressive when you start asking it questions about topics you already know. You'll notice that it's often wrong, but the bigger problem is that it's always confidently wrong.

Obviously it's still extremely impressive and much better than anything I've seen before - and it might mean we're only a few years away from something flawless - but I can't trust it for now.

(In theory, though, it might be easy to solve the current problem. The bot doesn't have to be right about everything, it just has to cite its sources. "I think that Napoleon was defeated by Wellington at the battle of Borodino. For more information, see this Britannica article. Click here to report if I made a mistake.")

Yeah I asked it a programming question and it suggested I could use both degrees and radians (for a 'double' parameter) giving literal examples (not just in text but in code) 'use 45 for 45 degrees, and 1.5 for 1.5 radians'. This is for Flutter's Transform.rotate and unless I've missed something, this is always in radians. Took me longer to find out than if I had just Googled it, although I admit I had been using it with success all morning for comparable questions.

If it's right 90% of the time and acts and sounds like it is right 10% of the time while being (slightly) wrong, that makes it practically useless.

I asked if how long the titanic was, and it gave a very good and confident answer. Including how it hit a polar bear and sank.

For some things it confidently gets completely wrong, you can correct it slightly and put 5-6 other prompts to arrive at a correct answer. This is not easy to automate though.

The inaccuracy and the confidence when they respond, are the worst aspects of these transformers.

Prompt it better, provide escape hatches (if I am not clear ask follow up questions), tell it not to improvise, provide more context, prime your prompt by referencing deep related material, provide examples of what you want it to do.

If you follow all this in your initial prompt, you will get vastly better responses... which is unsurprising. How would you react when you get a random DM from someone asking such an esoteric question, without surrounding context? (Is the person just role playing here, or is this a genuine research request for the purposes of a report?)

Can it answer "Don't know"? Or does it suffer from over-inflated ego, just like humans?

A lot of people on HN are poking holes in ChatGPT when they find something it does wrong. I have to imagine 20-ish years ago we’d be complaining about questions we tried that Google failed to give a good result for.

> For example, ask it to give you a minizinc model for the 8 queens problem.

But even a normal software engineer, is likely to confidently fail as something as niche as this. What percent of anyones work consists of questions like this? Even for the people who do encounter it, I’m willing to say not very much……

This doesn’t even take into account the state of this technology in 2,3, 10 years. A lot of people denying every advancement in this stuff are going to be saying it all the way into their obsolescence.

Look at you with your ability to downvote

I'm getting better (pre digested?) results for technical questions than google ever could. Last night it helped me with my redis replication info question, giving me the right commands to run.

I tried asking it some questions in German, and the answers read similar to auto-translated spam you often find on the internet. (If you look for stuff in German, a lot of results are often just auto-translated from English) So it seems it's already suffering from spam.

A thought just hit me: If AI researchers use text from the internet to train their auto-translators, and a lot of text on the internet is created with automatic translators, the translators will end up reinforcing their errors and develop a very distinct style, and since people read a lot of the autotranslated stuff, maybe people will also start writing in that style...

It's already there. you ask it to write an article and interject an ad about squarespace.

If you allow him to Google for results, why wouldn't you allow him to use ChatGPT?

So far ChatGPT has not given me any spam or advertising or malware!

That said, I saw a programmer comment earlier that they had spent hours unsuccessfully trying to solve a software problem in an area they understood, then they asked ChatGPT and it solved it correctly . . . the tone of the comment was rather deflated.

ChatGPT is way way better at many writing tasks than I am, but I try to not let my ego be dented. Should my ego be more threatened by ChatGPT, but not threatened by the existing translation tools (or Dall-E) which are similarly magical?

I don't think you can get too lazy by using chatGPT to help with coding. For simple stuff it usually gets it right and you can just copy-paste the code without thinking. Not that much different from just copy-pasting code from StackOverflow. Most IDEs can already auto-complete boilerplate code. chatGPT just does it better and faster.

But if it makes a mistake or you want a more complex program, you'll be forced to debug and learn how things actually work. It's also often confidently wrong in explanations, with errors and mistakes that are obvious to anyone who knows the subject well, or that don't hold up in the real world.

TL:DR; chatGPT is currently only useful for use-cases that should be automated anyway (simple programming tasks and boilerplate code), doing much more than that requires an understanding that chatGPT can't hand-wave away.

What do you mean "by do I show him ChatGPT?". He'll eventually find about it by himself.

Yeah, sounds like a good idea. If/when it becomes a thing people can finally skip reading the card and land it straight into the trash. Beware of the tsunami of autogenerated stuff to come upon the world, it will become tiring.

Perhaps writing (by hand) a smiley on a post-it would be more meaningful

I've found it similarly great for writing postcards and leaving cards.

In all of these situations having 30-50 words of fluent language with a friendly vibe is still much better than a generic "Wishing you well" or "See you soon".

I suppose the next internet needs to be built around networks of trust to counteract this. Everyone will be assumed to be spammers by default. Then you add whitelists and use network algorithms to determine if user X is worth your time.

I wonder how many years we have left until a given comment on any web forum is more than likely bot generated

How will websites like reddit, facebook and co be able to convince advertisers that they are not paying to show ads to bots? Maybe they will come up with countermeasures. Because how is that not threatening their hundreds of billion dollar business models?

> AI chat will become more and more accessible. Writing/renting/commissioning bots will be cheaper. Can you imaging arguing your case to a bot? To a team of bots run by the same org? The sinister side of me thinks this will quickly turn political and will also help eroding what's left of democracy

Astroturfing is already a strong problem here and on reddit, specially the later

And yeah, it will certainly be a problem, as right now they need to hire actual people to do it, they give them actual sheets with preworded arguments and rebuttals to use, this will certainly only make it easier once the tech is properly implemented

I wonder how many years we have left until a given comment on any web forum is more than likely bot generated