Strange answer from GPT

AI-generated summary

The discussion Strange answer from GPT revolves around a user’s interaction with GPT-4o bot. Jagster asked the bot to explain the differences between GPT-4, GPT-4o, and GPT-mini, and instead of a direct answer, the bot provided a code snippet showing function calls to web browsers for the respective model URLs. pfaffman chimed in, stating that the actual reason behind this response is unknown, and jokingly suggested that the code snippet might be the actual difference in the models’ code. Jagster found this explanation amusing and accepted it as a legitimate solution.

I know, this isn’t pure support question and Development or something else perhaps would be better. But because I’m really far away from a dev we are here.

GPT-4o bot by DAI and I asked it expalain differences between 4, 4o and mini. And because such topics can’t ne found from my forum I guided it to do a google-search. Yeah, I know — lousy prompting.

I got this:

<function_calls>

<tool_name>multi_tool_use.parallel</tool_name>

<tool_uses>[{:recipient_name=>“functions.web_browser”, :parameters=>{:url=>“https://openai.com/gpt-4”}}, {:recipient_name=>“functions.web_browser”, :parameters=>{:url=>“https://openai.com/gpt-4o”}}, {:recipient_name=>“functions.web_browser”, :parameters=>{:url=>“https://openai.com/gpt-4o-mini”}}]</tool_uses>

<tool_id>call_PG4cmAKuohcSsie52GHvxzt9</tool_id>

</function_calls>

Out of pure curiosity, nothing else: what happened?

From everything that I’ve read the answer to “what happened?”—whether the AI did a great job or a terrible job—is “No one knows.” And the people who do have answers made them up the same way people 2000 years ago explained eclipses.

My guess: That is the actual difference in the code that generated those models. :crazy_face:

I accept that as legit solution :rofl: