this post was submitted on 31 May 2025
0 points (50.0% liked)

No Stupid Questions (Developer Edition)

1030 readers
2 users here now

This is a place where you can ask any programming / topic related to the instance questions you want!

For a more general version of this concept check out [email protected]

Icon base by Lorc under CC BY 3.0 with modifications to add a gradient

founded 2 years ago
MODERATORS
[email protected]
0
Sharing AI-Aided Knowledge Beyond Corporate Platforms (programming.dev)
submitted 3 days ago by [email protected] to c/[email protected]
3 comments fedilink hide all child comments
 

Seeking Direction: Sharing AI-Aided Knowledge Beyond Corporate Platforms

As a Reddit (and RIF) refugee, I'm searching for a space to share various useful information where it can be easily found later. The challenge is that the definition of "useful" varies among individuals, and I suspect that Reddit and other "for -profit" moderators are overly influenced by corporate interests.

In the past, I spent considerable time figuring out how to accomplish tasks unrelated to my primary goals—tasks I usually only needed to do once. Now, I tend to ask AI tools like ChatGPT, Perplexity, Deepseek, or other available models to assist with the task at hand. I've learned that by doing so, I can condense days or even weeks of effort into just a few hours, if not less.

However, a significant issue is that these AIs don't currently learn from my questions, and the knowledge they provide isn't propagated beyond the AI itself, unlike traditional sources. The AI models offering this information are essentially static, and the context of the current session is typically lost quickly.

The solution I envision is to take the results of successful chat sessions and post them somewhere on the internet where both humans and AIs can access and incorporate the information into their knowledge and training. The problem is that this approach doesn't align with the posting models of conventional for-profit services like Reddit or Facebook. I tested Reddit again this morning and immediately had a post rejected for "low effort," even though it would have taken me a long time to develop the content myself.

I'm looking for direction on:

Where to share this AI-generated knowledge so it's accessible and beneficial to others.

How to structure these posts to fit within the guidelines of non-commercial platforms like Lemmy.

What communities or instances would be receptive to such content.

Any suggestions or guidance would be greatly appreciated!

top 3 comments
sorted by: hot top controversial new old
[–] [email protected] 2 points 2 days ago

Feels like building your own resource place would be fitting. Have you considered creating a webpage or repo or shared-writing primarily under your author instead of shared and hosted in a community?

[–] lurch 1 points 2 days ago

why don't you ask your AI, if it's so good. (intentionally no question mark.)

[–] [email protected] -3 points 3 days ago

This is the post I tried to share this morning as a reference for the type of information I want to be sure is available in the future:

✅ How to Enable Parameter Hinting in Neovim with lsp_signature.nvim and lazy.nvim

To display function signatures and parameter hints inline while coding in Neovim, follow these steps:

1. Add lsp_signature.nvim to Your Plugin List

If you're using lazy.nvim as your plugin manager, include the following in your plugin setup:

{
  "ray-x/lsp_signature.nvim",
  event = "InsertEnter",
  config = function()
    require("lsp_signature").setup({
      bind = true,
      hint_enable = true,
      handler_opts = {
        border = "rounded"
      },
      floating_window = true,
      fix_pos = true,
      hi_parameter = "Search",
    })
  end,
},

This configuration ensures that lsp_signature.nvim loads when you enter insert mode and provides a floating window with function signature hints.

2. Update Your LSP on_attach Function

Ensure that lsp_signature is attached when your LSP client attaches to a buffer:

local on_attach = function(_, bufnr)
  local bufmap = function(mode, lhs, rhs)
    vim.api.nvim_buf_set_keymap(bufnr, mode, lhs, rhs, { noremap=true, silent=true })
  end
  bufmap('n', 'gd', '<cmd>lua vim.lsp.buf.definition()<CR>')
  bufmap('n', 'K', '<cmd>lua vim.lsp.buf.hover()<CR>')
  bufmap('n', '<leader>rn', '<cmd>lua vim.lsp.buf.rename()<CR>')
  bufmap('n', '<leader>ca', '<cmd>lua vim.lsp.buf.code_action()<CR>')

  -- Attach lsp_signature
  require("lsp_signature").on_attach({
    bind = true,
    hint_enable = true,
    handler_opts = {
      border = "rounded"
    },
    floating_window = true,
    fix_pos = true,
    hi_parameter = "Search",
  }, bufnr)
end

Then, pass this on_attach function to your LSP server setup:

require('lspconfig').pyright.setup({
  on_attach = on_attach,
  -- other configurations
})

3. Restart Neovim

After saving your configuration changes, restart Neovim to load the new plugin and settings.

4. Test the Setup

Open a Python file and start typing a function call, such as ChatMessage(. You should see a floating window displaying the function's parameters.

This setup provides real-time function signature hints, enhancing your coding experience in Neovim. If you need further assistance or customization, feel free to ask!