Live data from Hacker News

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

news.ycombinator.com

381–390 of 752 posts

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

#381

Earlier quoted context omitted.

Has there ever been a case of a ToS so badly written that not having one would have been preferable? I'd be curious to hear about that story if it exists.

At a certain point in my life, I came to the conclusion that if something is important enough, it generally pays to: (1) either research the matter myself until I was satisfied that I understood the cost/risk tradeoff sufficiently; or (2) if I don't have the time or skills to do that, have the matter reviewed professionally. Both of which are alternatives to "doing nothing". Employment or other contracts, health deci…

"Ain't nobody got time for that"... that's how I roll.

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

#382
A really good use I have discovered with GPT is that it is fantastic at clarifying tabletop game rules. Inevitably, while playing a game, a scenario comes up that will require gameplay be paused to consult the rules. By simply typing up the scenario it will reliably output the correct solution to the problem.

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

#383

I am a full time language student, and I use GPT to have "conversations" in the language. I can give it a subject (e.g., going through airport customs) and practice my conversation skills. What's also fun is I can feed it a list of vocab that I want it to use, and it'll find ways to put the words in the conversation. I also ask it to go back, look at my responses, and correct for grammar etc. It's shocking how adept…

Ours might be the last generation that will bother to learn anything, as universal everything seem to be approaching. But I think there will be a premium on all things "human".

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

#384
post #369

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 sounds interesting. Can you share the prompts that you use to set up a session please?

I've tried this kind of thing and I usually just say something along the lines of "can you respond as a cbt therapist ", you can swap cbt with any psychological school of choice (though I think gpt is best for cbt, as it tends to be local and not require the deep context of psychoanalytic therapies, and it is very well researched so it's training set is relatively large and robust)

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

#385

Earlier quoted context omitted.

>Google is fucked The last year or two have proved to me that they deserve it. Their search engine is utter dogshit now. Ultra commercialised, full of ads, so hard to find a result that is actually what I searched for. Guess that's what Google level greed will do.

Agree. Try looking up travel passport renewal on Google: The first entire page of search results are ads and SEO scammers that charge high fees to fill in a passport application form all disguised as government affiliated services. The actual government passport web site isn’t even close to being top result. Excite, Yahoo, and Alta Vista are welcoming Google to search giants retirement home. We dread when the SEO gam…

the same for travel visas: it's full of scam websites, and official ones are often very well done, easy, fast.

I have been a google reviewer maaaaany years ago, and it looks like they just don't invest anymore in this.

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

#386
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.

This seems very plausible to me. The context window improved a lot between GPT-3.5 and GPT-4, and OpenAI clearly see value in increasing it further.

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

#387
post #380

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 sounds like a long running conversation. Are there problems with extending past the context window?

I haven't had any yet, it is a new conversation with Gpt4, so only a bit over a week old.

It still seems to give good advice. Today it built an itinerary for indoor activities (raining here) that aligned with some short-term goals of mine. No issues.

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

#388
In work it’s common for me to put together working prototype software to demo feasibility of some approach.

The knowns are libraries, languages and sometimes sample code.

Usual workflow is lots of Googling and reading documentation to get something out in a few days.

GPT saves me lots of time researching and has effectively replaced Google and StackOverflow. It allows me to design a plan of attack from “use these 3 libraries to do x” to a working prototype which I can then iteratively refine. It also is good at answering technical questions about library and language features. For example: “I have a pandas data frame, show me how to loop through it and access columns 3 and 4”. Once I see the API call is iloc I can research more.

However there are a few issues with GPT:

1. Makes up APIs that don’t exist.

2. Uses APIs incorrectly.

3. Not up to speed on the latest APIs, or maybe chooses not to use them?

For example I’m working with a library that has two functions: create_group() or get_or_create_group(). GPT seems to not acknowledge that get or create exists.

Some usage tips:

1. I usually tell ChatGPT in my first question is: “don’t respond with too much text or detail. If I need more clarification I will ask.”

2. Use Shift+Enter to formulate my initial question in detail. For example if I say “let’s write a Python app” it will respond with “sure Python is a great language to…”. So give it enough detail to get to the point.

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

#389
post #228

I have found it is quite good at configuring complex AWS IAM policies in JSON. Not perfect but it saved a bunch of time. There are so many other examples but I truly never reach to google first anymore.

Uff, how do you verify these? One forgotten slash and you have exposed more areas than you wanted.

You definitely still have to verify it. The AWS Policy Simulator is always consulted. But the way it can just start spitting out all the various permission groups, use wildcards correctly, is a time saver.

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

#390

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…

Can I ask if you have a prompt that you use for this?

I don't know what part of the prompt was meaningful and I didn't test different prompts. It seems just telling it exactly what you want it to be seems to work.

I asked it to give me advice on some issues I was having and just went from there.

Post reply on HN