Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

ChatGPT Plus

openai.com

Post reply on HN
Print view View original

881–890 of 1001 posts

Re: ChatGPT Plus

#881

Post by brmgb »

rootusrootus wrote: post #20
KaoruAoiShiho wrote: post #3

Is there never going to be a version with less restrictions and filters? That would really be worth paying for.

That would be fun. I understand why they want to limit liability, but it does put a damper on things. I let my kid sit next to me last night and ask ChatGPT various questions, with no coaching on my part. A fair number of them got canned responses suggesting it wasn't an appropriate question to ask. Too bad, I would love to have seen the ML attempt at philosophy. Instead it kept thinking he was trying to off himself.…

It's unending now. I just stopped using it. It either blatantly lies giving you hallucinated answers or refuse to answer. The amount of subjects it shies away from is staggering. You can't even include divorce in a prompt related to fiction because it's apparently unethical and insensitive.

I have never gone from very excited to extremely frustrated and pessimistic about a tool that fast before.

Re: ChatGPT Plus

#882

Post by aeonflux »

behnamoh wrote: post #637
aeonflux wrote: post #608

Earlier quoted context omitted.

Of course. I use this in Hammerspoon. The API call is simply in Lua.

How did you get the selected text in the focused app and replace it with the GPT response? I worked on it for hours and couldn't do it. I'd appreciate it if you could share that config.

If you want to go full circle you can send the ⌘-C and ⌘-V key events before/after they query. This will just send selected text and replace this with answer. I prefer not to do that, since queries are quite slow and I rarely block waiting for round trip. I also use vim and vim mode in lot's of apps, so replace works differently there.

I prefer to use clipboard as the exchange place. I select text, copy it, then query the service. Once the query completes I can see the answer in popup and can paste it to my current editing place.

This is the code:

  local hyper = {"cmd", "alt", "ctrl"}

  hs.hotkey.bind(hyper, "Y", function()
    local url = "https://api.openai.com/v1/completions"
    local api_key = "..."

    local headers = {
      authorization="Bearer " .. api_key,
      ["content-type"]="application/json",
      accept="application/json"
    }

    -- hs.eventtap.keyStroke({"cmd"}, "c")

    local message = hs.pasteboard.readString()

    local data = {
      prompt=message,
      model="text-davinci-003",
      max_tokens=32,
      temperature=0
    }

    hs.notify.new({title="OpenAI query", informativeText=message}):send()

    hs.http.asyncPost(url, hs.json.encode(data), headers, function(status, body, headers)
      local response = hs.json.decode(body)
      local answer = response["choices"][1]["text"]

      print(body)

      hs.notify.new({title="OpenAI response", informativeText=answer}):send()
      hs.pasteboard.writeObjects(answer)
      -- hs.eventtap.keyStroke({"cmd"}, "v")
    end)
  end)

Re: ChatGPT Plus

#884

Post by stavros »

irthomasthomas wrote: post #873
stavros wrote: post #858

Earlier quoted context omitted.

I'm not convinced that there's any substantial difference between the two.

Do you know if plain davinci-003 can continue long programming answers? I was using Chat to rewrite python scripts. It was it able to handle longish scripts easily by asking it to "continue", or simply "go on", if it ran out of room. But now they have blocked that ability since the Jan 30 update. It is quite a bit more painful now to have to break scripts up into chunks.

As far as I've seen, yes, GPT's output is quite long, and it could take anything I threw at it. If you try for your specific inputs, please let me know, I'm interested.

Re: ChatGPT Plus

#885

Post by irthomasthomas »

gdb wrote: post #374
qwertox wrote: post #145

~~~ To the ChatGPT Team ~~~ I'm currently receiving answers FROM OTHER USERS with this new version from 30 Jan, completely unrelated to my question: Q: Why is it easier for me to do endurance training on an empty stomach? A1: There are several things you can do to reduce the chance of getting a yeast infection: regenerate response: A2: There are many benefits to using cloud storage solutions such as Google Drive, Dro…

(I work at OpenAI.) Thanks for the report — these are not actually messages from other users, but instead the model generating something ~random due to hitting a bug on our backend where, rather than submitting your question, we submitted an empty query to the model. That's why you see just the answers and no question upon refresh — the question has been effectively dropped for this request. Team is fixing the issue…

Is the inability to "continue" a long answer also a bug? (Please say yes :)

Re: ChatGPT Plus

#886

Post by soerxpso »

Arkhaine_kupo wrote: post #826
int_19h wrote: post #769

Earlier quoted context omitted.

The effect is there, but it cannot be simplified as "left" vs "right" as OP claims. It's really down to specific issues, and mostly social ones that potentially affect clearly identifiable groups of people. Try asking it about same-sex marriage, for example.

> Try asking it about same-sex marriage, for example. Isn't equality a human right? I think its a worthy discussion, the ethical limits behind chat GPT, but that seems like a weird one to draw the line on no? I am more concerned about the fact it can generate malware, with incredible precisions and go around moredern anti virus techniques of detection without even hesitating but if you ask it to write a poem from the…

> Isn't equality a human right? I think its a worthy discussion, the ethical limits behind chat GPT, but that seems like a weird one to draw the line on no?

It's a polarizing issue that people have different opinions about. Seems dangerous to say, "it's okay that this is biased, because its biases are correct!"

For a clearer example where it exhibits a bias that's more objectionable, here: https://pbs.twimg.com/media/Fn5McpjacAMnWDr?format=jpg&name=...

Re: ChatGPT Plus

#887

Post by gooseus »

citilife wrote: post #659
gooseus wrote: post #289

Earlier quoted context omitted.

I find this a bit ironic considering conservative / religious ideology has a pretty long track record of attempting to create uniform societies by stamping out any outlying thought. That article you posted is rather extensive covering various ways they've been trying to mitigate issues of bias and toxicity, but not sure it's any evidence of bias against conservative / religious based ideology?

> conservative / religious ideology has a pretty long track record of attempting to create uniform societies by stamping out any outlying thought. Said on the internet, created by the most liberal democracy on Earth; founded by conservative puritans. Right in the constitution they enshrined the ability to have free speech, independent from government, church, and the people. > That article you posted is rather extens…

I'm not going to have an argument on HN with someone who is going to draw any kind of equivalence between Trump and Biden.

"Conservatives" right now are not anything like the conservatives who wrote the Constitution - they are actively (and explicitly if you listen to Trump) trying to throw out any part of the Constitution they don't like, including the part about separating church and state.

Personally, I'll take my AI with a healthy dose of liberalism (yes, the same kind that built the miracle we're communicating over right now) and I don't need it wasting any tokens and cycles struggling to justify why the Bible should taken any more seriously than the Illiad.

I believe you're either extremely deluded or operating in bad faith, but please feel free to continue this discussion with someone else.

Re: ChatGPT Plus

#888

Post by kkfdkerpoe »

pferde wrote: post #850
300bps wrote: post #281

Earlier quoted context omitted.

No. I'm a salaried employee. Marginal time/effort savings do not directly translate into more money for me. I am also a salaried employee and if I can save a minute of work time that’s one less minute I have to work. I have a body of work I need to complete and sometimes that takes me 40 hours and sometimes much more. The only way I can think of that $20 per month for increased productivity doesn’t help is if your co…

You don't need to complete the work. Your employer needs you to complete the work. If your employer gives you tools that make you work less optimally, they get less optimal work in return.

Exactly. It's entirely employer's responsibility to provide tools and equipment for the work, except perhaps stuff that you can keep, like tables, chairs and screens for home office. Only freelancers/entrepreneurs should pay for something like ChatGPT with their own money.

Re: ChatGPT Plus

#889

Post by kkfdkerpoe »

blagie wrote: post #356
Forgeties79 wrote: post #345

Earlier quoted context omitted.

The issue is once you buy a monitor for your work, they're then getting to rent it for free. If you need something to do your job better than they need to pay for it. You hurt yourself (financially) and you are contributing to a workplace culture where employees buy what they need. It's not just a monitor you're paying for! To be clear, I am not judging you. You did what was good for you and took the path of least re…

I don't care what they're getting as much as I care about what I'm getting. If I have a nice dual-monitor setup, in a business where everyone gets a 19" Dell, I will be more productive. That will lead to more promotions, lower odds of being fired, etc. I will come out ahead. Plus, I'll be happier. If my employer benefits too, how does that hurt me?

I wouldn't mind getting fired if I worked for a corporation that can't even provide proper screens for employees. Not getting equipment from employer is only acceptable for startups low on cash.
Post reply on HN