Ask HN: How are you using GPT to be productive? • Hacker News Board

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

#451

Post by typicalrunt » Sat, Mar 25, 2023, 3:08 PM UTC

As a non-judgemental sidekick. It helps with flesh out a random thought, it helps me understand a random coding problem, it helps me see why a vuln exists in a particularly difficult-to-read piece of code, and building outlines for reports and presentations that I'm too lazy to deal with. It is also starting to replace the random Google searches I used to do.

To boil it down, it's my "10-minute task" time saver.

And my use of it really picked up when I started using GPT4. It's head and shoulders above GPT3.5 in terms of quality and clarity of output.

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

#452

Post by throwthrowuknow » Sat, Mar 25, 2023, 3:10 PM UTC

fanagra32 wrote: post #371

applesauce004 wrote: post #328

Earlier quoted context omitted.

I agree with this statement a lot. Using Copilot saves you a lot of tedium if you are comfortable with the language already. If you are new to the language, then it might trip you up a bit (at least in its current incarnation). Here is an example where it helps. I tried to initiate a connection to a Mongodb server using Python. While i have used many databases before, I have never used Python and MongoDB together. So…

And you will have no idea whether the solution it presents to you is idiomatic or recommended or contains some common critical flaw or is hopelessly outdated. How can you find out? Back to alt-tabbing to the browser. Sure it may take a bit more time to get going, but then you'll get it right the first time and learn something along the way. Your copilot example is just another iteration of copy-and-paste some random…

Watch the demos where they provide GPT-4 with an API for performing search queries and calculations. These tool integrations are the next step and they will include specialized ones for using language and library docs. They could also be given access to your favourite books on code style or have access to a linter that they could use to cleanup and format the code before presenting it. The model is capable of using these tools itself when it is set up with the right initial prompt. Even now Copilot is pretty good at copying your code style if there is enough code in the repo to start with.

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

#453

Post by steelframe » Sat, Mar 25, 2023, 3:10 PM UTC

Hallucination really is a pretty serious problem. I've tried using ChatGPT to help my son play through quests on Octopath Traveler. About half the time the guidance it gives really does name places, characters, and objects that are in the game, but it combines them in such a way so as to be completely different from the way they are in the actual game. For example when I ask it about a quest it might say, "First you need to find Kit at his house with a blue roof which is in the northwest part of S'warkii. Then you need to go to the Whistling Cavern by heading north from the town of S'warkii." Which more often than not turns out to be completely wrong on all counts. Maybe I just need to get better at prompts.

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

#454

Post by PartiallyTyped » Sat, Mar 25, 2023, 3:12 PM UTC

ornornor wrote: post #438

PartiallyTyped wrote: post #430

Earlier quoted context omitted.

This is not whataboutism. GP identifies an action that analogous and holds certain properties as the original action, in the process illuminating how the issues of approach A exist in approach B.

But it is . "You're concerned about your data when using ChatGPT but you're probably using Google so your concerns are invalid"

They are not expressing that the concerns are invalid, they are expressing that one is held onto a higher standard than the other.

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

#455

Post by 29athrowaway » Sat, Mar 25, 2023, 3:13 PM UTC

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…

Interestingly enough, that was what ELIZA, one of the first chatbots was for.

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

#456

Post by tux3 » Sat, Mar 25, 2023, 3:13 PM UTC

ornornor wrote: post #397

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…

I’d be terrified to do this: - the insight into your mind that a private for profit company gets is immense and potentially very damaging when weaponized (either through a “whoops we got hacked” moment or intentionally for the next level of adtech) - chatgpt and other LLMs are known to hallucinate. What if it’s advice is wrong or makes you worse in the long term because it’s just regurgitating whatever at you?

>What if it’s advice is wrong or makes you worse in the long term because it’s just regurgitating whatever at you?

What if you talk to a human, and their advice is wrong or makes you worse off in the long term, because they're just repeating something they heard somewhere?

Here's my advice: Don't accept my advice blindly, humans make mistakes too.

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

#457

Post by qrybam » Sat, Mar 25, 2023, 3:14 PM UTC

deely3 wrote: post #296

qrybam wrote: post #182

I’ve been actively using it and it’s become my go-to in a lot of cases - Google is more for verification when I smell something off or if it doesn’t have up to date information. Here are some examples: • reviewing contract changes, explaining hard to parse legalese • advice on accounting/tax when billing international clients • visa application • boilerplate django code • learnt all about smtp relays, and requirement…

Can I just say that Im actually become scared reading your comment? Personally I would never ask chatGPT these questions because for me these questions are hard to verify, and knowing how often AI likes to hallucinate.. I just can't trust it. You mentioned 50/50 correctness in domain questions. I can't be sure that other hard to verify questions do not follow these percentage..

It IS dangerous. You must apply critical thinking to what’s in front of you. You can’t blindly believe what this thing generates! Much like heavy machinery, it’s a game changer when used correctly, and likewise it can be extremely damaging if you use it without appropriate care.

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

#458

Post by dmarchand90 » Sat, Mar 25, 2023, 3:17 PM UTC

Thorentis wrote: post #175

carlmr wrote: post #137

Earlier quoted context omitted.

So on my coding problems I haven't had much luck. It doesn't seem to know Bazel, the Rust code I asked about was completely hallucinated, but it did solve a problem with Azure DevOps I had. I think if the training set did not contain enough of something it can't really think of a solution. What is really nice though it's as you say the refinement of questions. Sometimes it's hard to think of the right query, maybe yo…

This could mean the future goes one of the two ways. Engineers get lazy and converge on using only programming languages which AIs understand or have been trained on, or we forget about this waste of time and work on more important problems to solve in society other than the lack of an AI to be our crutch. Sadly, I think the former is more likely.

Not so pessimistic. It's just one more level on the abstraction chain: assembly, C, scripting, chatgpt

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

#459

Post by throwthrowuknow » Sat, Mar 25, 2023, 3:18 PM UTC

roflyear wrote: post #356

mlboss wrote: post #350

Earlier quoted context omitted.

In very near future your IDE will send the whole codebase as context to LLMs. Then instead of thinking up all possibilities you can just ask. LLM will suggest multiple alternatives and you can select the best when and ask it to implement it.

Don't make stuff up. There is no indication that will happen.

GPT-4 has a model capable of using around 50 pages of written text worth of tokens (32,000) not sure exactly how many lines of code that translates to but it’s a lot. GPT-3 can use 4k so that’s a huge increase, the next version could be even larger and there are other ML techniques that allow for massive context lengths. Copilot already does a good job of refactoring code and knows enough about your code base to use your functions and methods. So what the other commenter said does not sound impossible to me.

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

#460

Post by ornornor » Sat, Mar 25, 2023, 3:23 PM UTC

tux3 wrote: post #456

ornornor wrote: post #397

Earlier quoted context omitted.

I’d be terrified to do this: - the insight into your mind that a private for profit company gets is immense and potentially very damaging when weaponized (either through a “whoops we got hacked” moment or intentionally for the next level of adtech) - chatgpt and other LLMs are known to hallucinate. What if it’s advice is wrong or makes you worse in the long term because it’s just regurgitating whatever at you?

>What if it’s advice is wrong or makes you worse in the long term because it’s just regurgitating whatever at you? What if you talk to a human, and their advice is wrong or makes you worse off in the long term, because they're just repeating something they heard somewhere? Here's my advice: Don't accept my advice blindly, humans make mistakes too.

Of course, but an AI can't explain how it got to what it's telling you. A human can, and you don't have to accept it wholesale; it's possible to judge it on its merits and argument. But no-one really understand how and why ChatGPT says what it does, so you can't trust anything it says unless you already know the answer.

In this discussion, a human has studied psychology and has diplomas or certifications to prove it, an ethics framework it must follow, and responsibility for its mistakes. ChatGPT has none of that, it just regurgitates something it got from the Internet's wisdom or something it invented altogether.

I'm not saying humans are never wrong, but at least their reasoning isn't a black box unlike ChatGPT and other LLMs.