Ask HN: How has ChatGPT affected your day to day work?
Would love to hear practical examples of how ChatGPT improved or otherwise affected your day to day and what do you think that means for the future of ChatGPT and your role.
Last month I needed to work in C/C++ which I usually don't, so ChatGPT helped me quite a bit, mainly to save time for researching, trial and error, etc. For example:
- I received a bunch of C files (~100) in a non-trivial folder structure from a code generator, however without a Makefile or something similar. GPT generated a Makefile based on the folder structure.
- I needed to add a couple of functions regarding reading and parsing a certain binary file structure. GPT was a good help here, too.
Additionally I was reading about some topics in linear algebra. I asked GPT to produce a intuitive explanation of the topics. This then helped me to work through the abstract description.
One simple way is it has superseded google/SO on my priority list for some reference lookups on topics I need to dabble in for work. (Like “Django custom function generate uuid”) Practically speaking, I’ve found this (most of the time) reduces the cognitive overhead of context switching. Less clicking, sifting, looking for recent answers, etc.
For slightly more complex reference on topics I’m dabbling in (Like “what’s the right way to use React hooks for this component”) the benefit of leveraging ChatGPT increases. In many cases you’re able to skip the step of generalizing your problem and you can address your needs from the “inside out”.
Inside out example: starting at some API method names and sample code for some libraries, rather than starting with a list of libraries or worse not knowing what kind of library you need yet.
Finally the place where it has had the most impact for me is as a force multiplier on efforts outside of my comfort zone as an engineer. If I have a side project idea, or if I’m trying to be ambitious in design at work, I can often discuss approaches at length with ChatGPT and walk away with several ideas, or even conclusions about how best to proceed without exhausting myself.
Replaces Google+StackOverflow by a large account now. I use it mostly for code generation.
Just today I had it write me SQL scripts for batch refactors / renames / replaces of column data and table column definitions and to generate a c# enum class for a table of response codes a payment processing gateway responds with. It has made me much more confident in my day-to-day job where I write web applications for clients.
Certainly speeds up integrations and anytime I have a bit of uncertainty as to how to solve a particular task which I have not come across previously - its a game changer!
I recently accepted a job offer and am preparing to move to another country. I need to write and respond to dozens of emails involving a lot of HR people, which I’m not used to at all, and ChatGPT helps me keep my writing polite and to the point. I think it’s perfect for producing boilerplate texts such as formal emails.
It has affected me at all either. I played with it a bit a few months ago, asked it show me code for PouchDB.js and it did. It was basically a copy and paste from their website without attribution.
After pondering it a bit I really couldn't come up with anything I wanted to use it for and haven't looked at it since.
as a translation tool it works perfectly
beside English grammar check, hindu tutorials, japanese news
latex - markdown - html/javascript - matjjax
python into and from python libraries
python to and from mysql
math formulas extracted from pdf research papers and translated into jupyter python code snippets
and helping with reading papers
with v4 and plugins I went from youtube tutorials to books to textbooks to papers in 4 months
- I received a bunch of C files (~100) in a non-trivial folder structure from a code generator, however without a Makefile or something similar. GPT generated a Makefile based on the folder structure.
- I needed to add a couple of functions regarding reading and parsing a certain binary file structure. GPT was a good help here, too.
Additionally I was reading about some topics in linear algebra. I asked GPT to produce a intuitive explanation of the topics. This then helped me to work through the abstract description.
For slightly more complex reference on topics I’m dabbling in (Like “what’s the right way to use React hooks for this component”) the benefit of leveraging ChatGPT increases. In many cases you’re able to skip the step of generalizing your problem and you can address your needs from the “inside out”.
Inside out example: starting at some API method names and sample code for some libraries, rather than starting with a list of libraries or worse not knowing what kind of library you need yet.
Finally the place where it has had the most impact for me is as a force multiplier on efforts outside of my comfort zone as an engineer. If I have a side project idea, or if I’m trying to be ambitious in design at work, I can often discuss approaches at length with ChatGPT and walk away with several ideas, or even conclusions about how best to proceed without exhausting myself.
Just today I had it write me SQL scripts for batch refactors / renames / replaces of column data and table column definitions and to generate a c# enum class for a table of response codes a payment processing gateway responds with. It has made me much more confident in my day-to-day job where I write web applications for clients.
Certainly speeds up integrations and anytime I have a bit of uncertainty as to how to solve a particular task which I have not come across previously - its a game changer!
After pondering it a bit I really couldn't come up with anything I wanted to use it for and haven't looked at it since.