Live data from Hacker News

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

news.ycombinator.com

611–620 of 752 posts

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

#611
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…

It's saved my ass this week coming up with coding exercises for a course me and some folks are working on. Has been a rough week. Depression flaring up. Creates a real mental barrier at times. GPT has helped a lot. I still will do the code myself and all that. Just came up with the written out ideas for exercises which really got me over the hump. It's incredible how helpful that was.

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

#612

I'm trying to use GPT to help me (and others) manage recruiting emails and the job search process. Right now, every time you start looking for a job, you start from scratch. Review old emails, search for relevant job boards, check HN, check LinkedIn, etc. The goal is to use GPT to automate outbound to companies to find you potential opportunities that match your preferences. Basically a GPT-powered recruiter for ever…

I tried to sign up but the only option is to sign in with Google which I don't want to do. Can I not just give you my email address?

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

#613

- weekly meal plan: I let chat gpt decide almost all my meals for a week given specific macro distribution parameters and I made a small script that takes the ingredient list and automatically orders them from the supermarket - explore tech ideas: when I have an idea about how to improve a specific part of a system by using something I have little to no experience with I use chat gpt to explore topics, get to know wh…

Could you share the prompts you use for the meal plans?

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

#614

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…

Curious how you work the prompts with the therapist persona? I'm interested in this. My main concern is GPT seems to struggle maintaining context after a time.

If you have time I'd love to hear how you approach this and maintain context so you can have successful conversations over a long period of time. Long even meaning a week or so... Let alone a month or longer

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

#616
post #230

Earlier quoted context omitted.

I’m unfamiliar with gpt and tokens, what would “skip prose” change?

The annoying habit GPT has of restating the question as the start of the answer. "How do I write a function in JavaScript to sort a list of cities by population grouped by region? GPT: To sort a list of cities by population grouped by region, in JavaScript, would at a high level require 3 steps...." Super frustrating when you just want the answer without the "polite professionalism"

If you can only work with GPT-3.5 model, the prompt that bumbledraven shared may still produce some explanations and provide no syntax highlighting. To solve this, you can add: "Skip prose. Skip explanation. Answer in a single code block in markdown."

Also, if you're using the playground, I'd recommend keeping the temperature low (I normally set it to 0 for this task). This will prevent any extra information such as test data, from being included. From my experience, setting the prompt I shared earlier as the system prompt produced more consistent results. However, whatever I shared is based on my own trial & error, so I'm not sure if this will work for you/in general.

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

#617
post #519

Earlier quoted context omitted.

They are not deciding what is good for us, they decide what is good for their public image, and that kind of controversy is certainly not something they'd like to venture into.

Nothing controversial about porn.

I'm so confused by this statement. I mean I have no issue with pornography or sex workers but pornography is absolutely controversial. I mean... Parents are trying to get the statue of David removed from a high school in Florida because they consider it pornographic. That's controversy and that's not even pornography.

Controversial: giving rise or likely to give rise to public disagreement.

Maybe you were being silly and I misunderstood your intent in your reply

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

#618
post #525
post #437

Earlier quoted context omitted.

It / OpenAi are not "deciding what is good and bad for us", it is deciding what services they want to provide or not provide. Your pontificating is doing more "deciding what is good and bad for us" (grousing about it's inability to identify the pornstar you're horny for today & dressing it up as some kind of moral high ground) than it is. There are plenty of open source LLM and "AI" models or research to build your o…

It seems like you think you have a moral high ground. Being horny for pornstar isn’t inherently bad.

It's not bad at all, really. But, it's a privately owned company that doesn't want to incorporate that material into their product. That is totally their right and doesn't have anything to do with them deciding what is right or wrong. I mean, ir be lying if I said I don't enjoy porn now and then. I did a LOT more when I was younger. But, I absolutely get why they don't want to bring that into their product.

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

#619
post #471

Earlier quoted context omitted.

You have no idea if the alternative code you would have written would have been idiomatic or had some critical flaw. We have 50+ years of software engineering wisdom to deal with these issues. Testing, Fuzzing, version control, code reviews, the whole gauntlet.

I mean... I certainly know which languages I can write idiomatic code in and which I cannot. I can't know that my code will be free of critical flaws, but I do understand the common sources of flaws and techniques to avoid them, and I'm quite confident I can build small features like this that simply aren't vulnerable to SQL injection, on the first try and without requiring fuzzers or code review: https://infosec.exc…

I'm confident enough in most languages I write in to recognize correct code. But I am not usually so familiar that I can conjure the exact syntax for many specialized things I need. Copilot is just a much quicker way to get what I need without looking it up.

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

#620
post #412

Earlier quoted context omitted.

Which language is it struggling with?

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 Java.
Post reply on HN