Often when prompting for a deep-research job, I try to give context or simply add my thoughts about a certain subject matter or an observation I have made (leading me to asking a DR question). In most cases these are hypotheses or just anecdotal evidence. However in ChatGPT’s deep research response the AI tries to either directly answer these questions, as it should; or it includes these anecdotes literally in some way. Then these hypotheses are formulated with a positive tone, as if the AI deliberately tries to include my “research material” as a fact. Perhaps this is a consequence of being tuned to be in “grad student essay” mode. Or, perhaps, of being journalist mode: A journalist came up with a viewpoint and some notes in his/her research and tries to include it in the text. ChatGPT DR does just that.
Nothing against it, just want to know if this is true .
My personal countermeasure, to avoid that bias, is simply to run an o3 job with web search first. It is faster, more concise, more to the point (following my instruction prompt) and does not try to confirm my assumed viewpoint