Beguène Permale

undefined

[Beguène Permale @beguene]

Live editing a react app with plain English featuring
@OpenAI Edit GPT, @nextjs and precedent template from @steventey (speed 1.5x)

[Beguène Permale @beguene]

LLM will create Kodak moments for many

[Lady Galadriel @ladygaladriel21]

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!! 😅😂🤣

[Beguène Permale @beguene]

@TheSeaMouse so cool ! How reliable is it ?

[Beguène Permale @beguene]

Before AI it was publish OR perish.
After AI it is publish AND perish.

[Beguène Permale @beguene]

It is far easier to learn the real subject properly than to learn the imitation badly

[Beguène Permale @beguene]

Is GPT just another Grand Parlor Trick ?

[Beguène Permale @beguene]

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

[Beguène Permale @beguene]

Soon we will have more podcasters than listeners

[Beguène Permale @beguene]

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

[Beguène Permale @beguene]

Creating React components in parallel with @OpenAI GPT-3

[Beguène Permale @beguene]

A prompt engineer is a restricted software engineer with a less restricted language 😆

[Beguène Permale @beguene]

@MichaelRouveure @OpenAI @nextjs @steventey With a custom elisp function in emacs. See my followup tweet above

[Beguène Permale @beguene]

Live editing a react app with plain English featuring
@OpenAI Edit GPT, @nextjs and precedent template from @steventey (speed 1.5x)

[Beguène Permale @beguene]

@sandstormcap @OpenAI @nextjs @steventey See my followup tweet above

[Beguène Permale @beguene]

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

[Beguène Permale @beguene]

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

[Beguène Permale @beguene]

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 https://t.co/0PywdGm8qn.

[Beguène Permale @beguene]

next experiment: a Node.js backend 🧐

[Beguène Permale @beguene]

This all works by sending the file buffer + the instruction to the openai api edit gpt https://t.co/t6CMU17NRM which does all the work 😆. It then replaces the file with the api response and so on.

[Beguène Permale @beguene]

The code used to do this https://t.co/9m2AfQza7Q
Instructions are at the top of the file
@steventey
@harishkgarg
@sandstormcap

[Beguène Permale @beguene]

Live editing a react app with plain English featuring
@OpenAI Edit GPT, @nextjs and precedent template from @steventey (speed 1.5x)

[Beguène Permale @beguene]

Good software engineering is about finding the right trade-off between speed and quality.