For simple questions you can just ask ChatGPT. For complex questions the Stack Overflow moderators would have closed your question for lack of focus. Unless a question reads like a tech spec it is ambiguous and unanswerable to them.
Being unable to clearly mark the bounds of relevancy for answers (in a structured way that affects search) is a major weakspot of SO.
One of the ingredients that made GenAI possible was a massive quantity of public, relatively high quality data (the internet).
We crowd sourced that over decades. If we transition to only interacting with AI agents in private as consumers, the corpus will fail to grow and update.
If it wasn’t trained on a specific newer API or Cloudformation/Terraform/CDK construct, with 4/4o, I just give it the link to the relevant documentation and tell it to use the links to help it create the right code.
I purposefully chose something obscure that I knew was a new feature that wouldn’t be in the training data. Even then I had to force it to search the web
https://chatgpt.com/share/67992b79-f047-441a-809c-f151b2e511...
The PDF had multiple columns, and while ChatGPT seemed to figure that part out, it couldn’t do the logic part. Had it been in an easier Format to deal with, I would have just used to spreadsheet.
I had to explicitly tell it to verify its sources on the web and use Python
https://chatgpt.com/share/27ffea74-b3c0-478e-a6f4-3aca9e3e64...
Then I just changed the initial prompt
https://chatgpt.com/share/5f44924f-4b2c-4d26-92e2-cf3b398cf2...
“ Create a list of presidents with the first column being the year they were born and the second their name. Order the list by the first column.
Use Python and verify the ages on the web”
2. Checks Google/SO and no answer
3. Figures it out themselves
4. Blogs about that
5. AIs that search pick it up first but eventually it ends up in training.
As well as AI teams paying for content for training.
Some studies show that the number of sites with AI blockers at their robots.txt has dramatically increased!
Right now, some companies are trying to ignore robots.txt, but after regulations...