One and half years ago, in Japanese Twitter this method gathered a bit of attention.
It's called pawahara prompt (パワハラプロンプト, power harassment prompt) because it's like your asshole boss repeatedly saying "can you improve this more?" without any helpful suggestions until the employees breakdown.
Many people found it could improve the code base at some point even then, I think now it works much better.
It's very not accurate, but sometimes instructing to return pyautogui code works.
prompt: I attach a screenshot (1920x1080). Write code to click the submit button using pyautogui.
attachment: <screenshot>
reply:
import pyautogui
pyautogui.click(100, 200)
I confused those features of the native language server, so here's the summary:
- Go-to-Definition: For variables, jump to the declaration. For functions/classes/types, jump to its types or implementation.
- Go-to-Type-Definition: For variables, jump to its type declaration instead of the variable declaration.
- Go-to-Implementation: For interfaces/abstruct classes, jump to (multiple) implementations of the method. For compiled TypeScript file (like them under node_modules), jump to its implementation rather than .d.ts files.
Does anyone know if it's possible to run Strudel code on VS Code (or NeoVim)? Tidle Cycles has add-ons where I can play/stop updated code or part of code with ctrl(cmd)-. and ctrl(cmd)-space. I mean, one of Strudel strong point is the browser based rich visualization, but I just want to edit JS code with my favorite editor.
> For example, the other day, it completely forgot about a database connection URL I had given it and started spitting someone else's database URL in the same session.
Something similar happened to me.
Our team managed multiple instances for our develop environment.
I was working with the instance named <product>-develop-2, and explicitly told Claude Code to use that one.
$ aws ec2 describe-instances ...
<product>-develop # shared develop instance
<product>-develop-2 # a development instance where a developer can do anything
<product>-develop-3 # another development instance
<product>-staging
<product>-production
Claude used the correct instance for a while, and wrote multiple python one-off scripts to operate on it.
But at some point, without any reason, it switched the target to the shared one, <product>-develop.
I should have checked the code more carefully, but I didn't pay enough attention to the first few lines of dozens lines of code
where all config were written,
because it seemed always the same and I was mostly focuced the main function.
import boto3
import os
...
AWS_REGION=xxx
AWS_PROJECT=yyy
EC2_INSTANCE=<product>-develop # <- at some point this changed without any reason
S3_BUCKET=zzz
...
def main(): # <- all my attention is here
# ~100 lines of code
As a result, it modified the shared instance and caused a little confusion to my team.
Luckily it wasn't a big issue.
But I was very scared if it targeted the production,
and now I'm paying most attention to the config part rather than the main logic.
It should not be possible to connect to the production database from your local machine, especially if the tool you are using to write and run your code is configured by polite entreaties that can be ignored willy nilly.
I mean, yes, our team and I were too lazy to set up things correctly cause we were hurried to ship some AI product only to be replaced later by OpenAI's much better version.
A part of me starts liking this kind of style because it feels more human... I'd rather wanna be bothered by some cringy writing than by those em dashes...
Honestly, I sometimes use heavy thinking models only to avoid wasting tokens on my expensive pro plans. In many cases, I prefer using quicker models to discuss something, gain better ideas about the topic, do "my own research" using Google, then discuss again. ChatGPT Pro mode is helpful, but it's too slow, and I have no idea what they say is true (even with sources) or I'm familiar with the topic so I can research faster myself.
I use coding agents often, but I don't burn all the tokens out of my Claude Max plan and ChatGPT Business plan with two seats.
One thing I like about the current AI craze is that several services start to provide user-oriented services again, like 90s and 00s.
Search engine for AI returning only relevant results (no ads and promotions),
online stores showing only relevant items,
news articles in non-clickbait, clear and concise style.
I'm not confident the current AI craze will be net positive for humanity.
But one possible good outcome could be that
many people prefer simple chat UI to interact with services,
most companies have to adopt them and are forced to provide simple, straight, no-nonsense content instead of what they want to sell,
while LLMs are just commodity so unnamed Chinese companies can provide models as good as the one from the most VC-funded company
so they can't enshittify the UX.
reply