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

151–160 of 752 posts

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

#151

Post by bennysonething »

_nalply wrote: post #115
DoingIsLearning wrote: post #66

Earlier quoted context omitted.

> Generally rewriting emails for clarity... This is the sort of thing that will force a lot of legal teams to shutdown access to GPT-4 api/gui from internal networks. Ppl never think of unintended consequences. Ask it a prompt fine but don't provide internal information as an input.

This is one of the causes there's a push to run your own engines for large language models: if you run your own service you can control the environment, data and reproducibility.

This is exactly what my employer is doing, they pay so that our internal data (from employee queries) does not become part of the model. They've blocked the public chat gpt etc.

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

#152

Post by pragmatick »

exolymph wrote: post #129

I'm a writer (copy, social, all-purpose) at a startup. I've been using GPT4 via Lex.page to generate crappy first drafts which I then improve and expand. It can speed up the process quite a bit, but needs handholding and someone to add in personality.

What's lex.page? The landing page doesn't give any information, just requires me to login using Google.

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

#153

Post by zacte »

xgbi wrote: post #145

I asked him to create new plausible scenarios for an X-Ray training program I'm writing. It was not THAT plausible, but it filled the placeholders I have in my UI quite well and he actually used other words related to anatomy than thos I provided in an example. Also, I asked him to output the resulting scenarios according to a vague json schema and he complied. Copy/pasted it in my JS front and it went without a hitc…

I found it interesting you're starting anthropomorphizing it.

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

#154

Post by e-brake »

For compliance, I have been using it to complete cheesy "security training" videos and quizzes that we are forced to watch in the organization for insurance purposes. The videos are so bad, the training is ineffective anyways. We used to load them all on mute at the same time every quarter, click through as fast as possible to get them out of sight, which is considered a metric for how valuable the videos are (how much we need to improve). ChatGPT usually gets it right! Hooked up to Playwrite.

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

#155

Post by nicbou »

I use it to write boring German letters that don't need a human touch. It saves me the trouble of finding the right words in a foreign language. It made dealing with the bureaucracy a lot less dreadful.

I think it might be good at answering "why" questions since Google completely gave up on that.

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

#157

Post by stocknoob »

nomilk wrote: post #136
awestroke wrote: post #133

Earlier quoted context omitted.

You and I have very different ideas of what makes a good commit message

I’m interested to hear more. Can you give an example or two.

My take: Messages like this...

> Updated Gemfile.lock and added new dependencies (coderay, concurrent-… …ruby, crass, date, pry, method_source, public_suffix, puma, nio4r) and updated existing dependencies (rack-test, regexp_parser, xpath, nokogiri, racc, pg). Also added new files for a user authentication feature.

Describe the "what" but not the "why". Even "user auth wip" would be helpful. It's like having autogenerated code comments like:

// initialize variable i for later use in a loop

int i = 3;

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

#158

Post by arwhatever »

whateveracct wrote: post #38
arwhatever wrote: post #5

I’ve been using it to generate bash scripts because I don’t know bash scripting, and also have it generate regexes for me to search for code references in a programming language where the “find all references” functionality don’ doesn’t work quite well.

I didn't know bash scripting and then I wrote some scripts and then I knew bash scripting and use it for lots of stuff. Has ChatGPT resulted in learning by doing for you?

I guess I use ChatGPT similarly for Ruby and for Rust, but with the only difference being that in my mind I intend to “learn” those two.

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

#159

Post by nomilk »

stocknoob wrote: post #157
nomilk wrote: post #136

Earlier quoted context omitted.

I’m interested to hear more. Can you give an example or two.

My take: Messages like this... > Updated Gemfile.lock and added new dependencies (coderay, concurrent-… …ruby, crass, date, pry, method_source, public_suffix, puma, nio4r) and updated existing dependencies (rack-test, regexp_parser, xpath, nokogiri, racc, pg). Also added new files for a user authentication feature. Describe the "what" but not the "why". Even "user auth wip" would be helpful. It's like having autogene…

GPT can struggle to see the forest from the trees. For example, if generating a dozen or so files with `rails g scaffold post` a GPT-generated commit message may simply list all the individual items "Created new post views, new post controller, new post model.. etc" when "Generated a posts scaffold" would have been more general and useful message.

GPT sometimes 'sees' the bigger picture though, for example when I commit a new rails app, instead of listing the individual files, it instead generated: "Added all files for a new Rails application, including controllers, models, views, tests, and configuration files." It could have said "new rails app", but it wasn't too ineloquent.

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

#160

Post by menacingly »

carlmr wrote: post #137
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…

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…

My experience is almost completely the opposite. My likelihood to dive into something new is significantly higher now.

It might help to approach it from top down? Usually, if I'm asking a technical question, I want to apply my deeply understood principles to a new set of implementation details, and it has amplified the heck out of my speed at doing that.

I'm kind of a difficult to please bastard, a relatively notorious meat grinder for interns and jr devs, and still I find myself turning to this non-deterministic frankenstein more and more.

Post reply on HN