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

Ask HN: How are you using GPT to be productive?

news.ycombinator.com

Post reply on HN
Print view View original

691–700 of 752 posts

Re: Ask HN: How are you using GPT to be productive?

#691

Post by richardw »

cutemonster wrote: post #672
andsoitis wrote: post #184

Earlier quoted context omitted.

> I don't think it's actually reasoning about things at all, just providing a statistically plausible response to prompts. It turns out that humanity’s problem might not be that AIs can think but rather that humans believe that AIs can think. One might even go so far as to say there’s a real danger that we hallucinate that AIs can think, to our detriment.

> problem [...] that humans believe that AIs can think Definitely some people are going to believe this, eventually? People already bow to statues and worship various invisible gods -- the AI programs would be so much simpler to start worshiping? When they can speak (if there's a loudspeaker) and generate text about them being alive and don't want to be switched of. And that everyone should obey their command. -- Wai…

You will not need 15 years - I'd give it the next election. Someone just needs to turn Q into a chatbot and we're basically there.

Re: Ask HN: How are you using GPT to be productive?

#692

Post by roflyear »

sd9 wrote: post #681
roflyear wrote: post #678

Earlier quoted context omitted.

It's true, but there is no indication that GPT can explain larger concepts for you, and negative indication it will be able to do it accurately. It can't even explain small code to me unless it is something that it has been trained on. Often it gets even simple things wrong, either obviously, or worse, subtly wrong.

I agree that this is the part that needs more work, and is most uncertain. Increasing context windows seems like a fairly straightforward computational challenge (albeit potentially expensive). On the other hand, whether or not we can scale current models towards "true understanding" (or similar), is a total unknown atm. I still think we will get useful things from scaling up current models though. I've already got a…

> can scale current models towards "true understanding" (or similar), is a total unknown atm.

Right, but it's no more known than before GPT models IMO. It's the same unknown.

I don't mean to imply these language models are not impressive. They are pretty impressive.

Re: Ask HN: How are you using GPT to be productive?

#693

Post by maremp »

thih9 wrote: post #594
dr_dshiv wrote: post #281

Earlier quoted context omitted.

Risky vs what? Googling? Not doing anything? Waiting for a therapist? It’s extremely sensitive to human emotional dynamics. It is also extremely biased toward non violent communication, which is very hard for humans.

As risky as any other health related self help, plus the added risk of unreliability. When GPT proves itself to be reliably beneficial, then therapists will use it or recommend it themselves. Until then it’s an experimental tool at best.

I would say self-help is quite unreliable already, more unreliable doesn’t make it much worse.

The authority argument is pointless. The therapist must value person’s wellbeing above their continued income for this to apply. In theory they should, but it would take a lot to convince me and I would want to know what’s the incentive behind such a recommendation. An to be clear, I’m not saying LLM can be your therapist.

Re: Ask HN: How are you using GPT to be productive?

#694

Post by mbar84 »

yosito wrote: post #375
hermannj314 wrote: post #349

I have a few conversations going. My most productive is a therapy session with ChatGPT as therapist. I told it my values, my short term goals, and some areas in my life where I'd like to have more focus and areas where I would like to spend less time. Some days we are retrospective and some days we are planning. My therapist gets me back on track, never judges, and has lots of motivational ideas for me. All aligned w…

This is fascinating to me. For me the value of having a therapist is having another human being to listen to what I'm going through. Just talking to the computer provides little value to me at all, especially if the computer is just responding with the statistically likely response. I've had enough "training data" myself in my life that I can already tell myself what a therapist would "probably" tell me.

I imagine there is significant value alone from stating your situation explicitly in writing.

Re: Ask HN: How are you using GPT to be productive?

#695

Post by readonthegoapp »

barbarr wrote: post #40

For coding, I've been using it like Stack Overflow. It really decreases my barrier to doing work because I can ask lazy follow-up questions. For example, I might start out by asking it a question about a problem with Pandas like "How do I select rows of a dataframe where a column of lists of strings contains a string?". After that, GPT realizes I'm talking about Pandas, and I'm allowed to ask lazy prompts like "how d…

can you get at least one snarky, a-holish response along with the useful info to really give you that authentic SO feel?

Re: Ask HN: How are you using GPT to be productive?

#696

Post by wnkrshm »

roflyear wrote: post #679
throwaway4aday wrote: post #671

Earlier quoted context omitted.

Cool, if you don't want to talk about it that's ok. In that case I'd suggest looking up one of the various prompt libraries and learning from there.

I'm just not talking about trying to fish an accurate answer. I think you can do that. I'm talking about getting an answer about something that requires an interaction that gets the model to "understand" the problem (like you would a person) - which GPT can't do.

Something akin to: Here is a niche mathematical problem that does not fit any existing solutions/publications, we need a working but not necessarily optimal solution to do this. ?

Re: Ask HN: How are you using GPT to be productive?

#697

Post by wnkrshm »

ChildOfChaos wrote: post #504
ornornor wrote: post #502

Earlier quoted context omitted.

> If i worked at openAI and had full access to everyones chats, I would get bored within five minutes and not even want to read anymore. Yes, obviously. But that's not what I'm worried about personally. I'm worried about the weaponization of this data in the future, either from OpenAI's greed to create the next advertising money-printing machine or from the data leaking through a breach. And because the interface wit…

Yes, I would be fine with this. Not that much different from the current fingerprint techniques, it's just that on steroids but I don't understand the issue.

If people can automatically distill what motivates you, they can produce automated lies.

The best deception is one where the victim is self-motivated to believe it.

Re: Ask HN: How are you using GPT to be productive?

#699

Post by throwaway4aday »

roflyear wrote: post #679
throwaway4aday wrote: post #671

Earlier quoted context omitted.

Cool, if you don't want to talk about it that's ok. In that case I'd suggest looking up one of the various prompt libraries and learning from there.

I'm just not talking about trying to fish an accurate answer. I think you can do that. I'm talking about getting an answer about something that requires an interaction that gets the model to "understand" the problem (like you would a person) - which GPT can't do.

Consider how long our comment thread is and I still don't have a clear idea of what you're talking about or how to help you.

Re: Ask HN: How are you using GPT to be productive?

#700

Post by majewsky »

jjeaff wrote: post #620
jhugo wrote: post #412

Earlier quoted context omitted.

I've had similar experiences when testing it out with Rust, Java and Go. Once I got beyond basic stuff, very little of the output was of a quality that I would consider remotely acceptable, and the work to bring it up to standard was basically equivalent to just writing the code in the first place (which, come on, typing is not even the time-consuming part of engineering).

It makes sense that it wouldn't be very good at Go or Rust since both are rather rare languages in the open source world that copilot is trained on. When I did my first go project a few years ago, I had the hardest time finding even basic examples like how to parse a json string. Rust is even newer and less used. But java is the 3rd most popular language for GitHub projects so I would think it would do better with Ja…

There are over 50,000 and over 40,000 repositories just on GitHub that contain Go and Rust code, respectively. [1] Among them, some truly massive projects like Kubernetes for Go or Servo for Rust. I will freely admit your argument for new and/or obscure languages like Hare, but Go and Rust are not "rare" under any reasonable definition of the word.

[1] https://github.com/topics/go https://github.com/topics/rust

Post reply on HN