undefined

France
Joined January 2011
Live editing a react app with plain English featuring @OpenAI Edit GPT, @nextjs and precedent template from @steventey (speed 1.5x)
27
79
21
704
117,414
LLM will create Kodak moments for many
2
116
Beguène Permale retweeted
A classic is a book you keep turning the pages waiting for something to happen and find that you have turned the last page without anything ever happening!! 😅😂🤣
1
2
381
Before AI it was publish OR perish. After AI it is publish AND perish.
2
1
2
426
It is far easier to learn the real subject properly than to learn the imitation badly
1
314
Is GPT just another Grand Parlor Trick ?
1
238
Trying to make ChatGPT behave like a random number generator. Its output is obviously not random but it's not nonsensical. It always outputs a value different than the previous output. It seems like it tries to maintain the expectation of the initial distribution
1
328
Soon we will have more podcasters than listeners
1
1
3
337
Creating React components in parallel with @OpenAI GPT-3
1
3
12
1,055
It’s not perfect, for example the footer is not sticky bottom. This uses a custom prompt just for React with the OG GPT-3 model to emulate ChatGPT
2
295
A prompt engineer is a restricted software engineer with a less restricted language 😆
1
3
398
Creating a simple node.js api backend with @OpenAI GPT. The js code generated is exported to a new file with the command 'org-babel-tangle', shell cmds are executed with C-c C-c. Chatting with GPT like this looks a lot like literate programming
1
1
1
6
3,126
This could be really valuable, since interacting with GPT leaves a trace, all development processes are recorded and therefore reproducible. Literate programming makes everything more readable, maintainable and reproducible www-cs-faculty.stanford.edu/….
1
2
275
Note that I tried around 5 prompts before that, the js and shell code output was correct, but the org mode format to output the code evaluation result in external files was not correct
1
234
next experiment: a Node.js backend 🧐
2
481
The code used to do this github.com/beguene/emacs-gpt… Instructions are at the top of the file @steventey @harishkgarg @sandstormcap
Live editing a react app with plain English featuring @OpenAI Edit GPT, @nextjs and precedent template from @steventey (speed 1.5x)
6
1
17
1,716
This all works by sending the file buffer + the instruction to the openai api edit gpt beta.openai.com/docs/api-ref… which does all the work 😆. It then replaces the file with the api response and so on.
1
2
273
Good software engineering is about finding the right trade-off between speed and quality.
1
329
Seeing how developer tools improve daily, the advantage of having correct thinking skills over good typing skills will become even more pronounced.
2
379
red flag for a website: having an hyphen in the domain name 😞
1
2
272