81–90 of 752 posts
I'm now looking into other areas where it can help me automate easy but tedious tasks.
Some people still doubt its usefulness. I don't.
* Give me a bash one-liner to generate a secure random string * I'm using a NextJS middleware function by exporting it from my page component like this ... Here is the middleware source ... But I get this error ... * How can I tell if my site is running in production in NextJS? * NextJS says localStorage is not defined. What should I do? * Please adjust this Prisma schema so that there is an index on github_id * How…
awk and sed are great examples, I find them critically important just infrequently enough I barely have any idea how to use them.
or the once in 2 years I need to do something complex in a spreadsheet, a natural language description of the problem is easier for me to remember than some sequence of vlookup
- Web scrapping
- Web crawler
- Trying out Rust
- Trying out pytorch and training models for computer vision problems
This is all stuff that would have taken me several weekends of reading docs and geting familiar with libraries.
Now it suddenly becomes a few hours because the discovery of the right tool is semi-instant and although the code it provides is often wrong it generally puts you in the right direction.
My intuition is that it's a lot better at outputting viable Python and JS code than other languages, perhaps there is bias in how much data of other languages it has access to.
- Asked which config files handled sleep mode when lid is closed and kept fixing it and asking for more possible locations until it fixed my issue (going into sleep during boot before user login if laptop is closed even with externals)
- Asked for a list of KDE config files I should track in git
- Copy pasted a list of ~/.config files and directories and asked ChatGpt for descriptions. Used those for commit messages to build up the initial dotfiles repo for KDE plasma and a whole bunch of other stuff that would have taken hours
- Asked it how to write a bunch of journalctl queries
- Queried it about some log lines I've been seeing in journalctl and had it guide me through troubleshooting using some terminal commands it came up with. Turned out to be a problem with nvidia-drm.modeset in kernel configs
- Asked it to guide me through a dozen awesomeWM customizations ranging from new code from text descriptions to edit suggestions to fix bugs in behavior I've described. Stuff like custom if/else trees handling setup specific scenarios (logic for clamshell open and closed with one or more externals connected by ID) are a breeze.
- Asked it for tips on how to use awesomeWM best and which keybindings to customize
- Code up the message passing from a firefox extension to a native Rust CLI (like the 1password extension) that uses remoc to pass through messages from all tabs to a single daemon over platform specific interprocess communication
AKA Google is fucked.
Mostly just asking stuff directly on https://chat.openai.com/chat . Last 8 requests were (all successful): - Asked it to improve a HN comment I wrote. - Asked about an idiom I couldn't remember, by saying it in other words. - Asked it to dumb down some things about options (finance) I didn't understand. - Asked it if I could use the eBay API to list my purchase history (you can, and it knew how). - Asked it to genera…
Completely off-topic, but do you like prisma, and how are you using it (scale, complexity, solo vs team, etc). I toyed around with it a while back, and it looked potentially awesome, but different enough that I was worried about using it on a work project in case it failed in some use case. Im so sick of the SQL ORM situation in Typescript, but Prisma might have an answer.
lesson: {
select: {
id: true,
slug: true,
title: true,
mapped_sections: {
select: {
id: true,
slug: true,
section: {
select: {
id: true,
title: true,
course: {
select: {
id: true,
slug: true,
title: trueMe: what do you think about Robert Frost GPT: I speak the road plausibly travelled.
On the other hand, it can explain certain complicated concepts extremely easily. I like asking it questions when I just want a general answer as opposed to something that must work.
Another one I use it for is saying “Rewrite this code to run on multiple cores”. Really saves me a lot of Googling time as these are things I want, but I don’t find much pleasure in actually writing code.
I’ve also used it to generate some proof ideas while I’m going through exercises in Baby Rudin. Or to check a proof I’ve come up with if it makes sense.