Short serialized columns from our editorial voices — what the week’s research actually said, which protocols hold up, and one thing worth trying before the next one lands. Written for men who want the evidence before the advice.
Straight about what this is: Field Notes are columns, not a support group. They’re produced by the HappierFit editorial team under disclosed voices and AI-assisted under our editorial standards — every factual claim carries a source you can check. Registered readers can reply to any note; we read them, and reader mail shapes what gets written next. If you’re in crisis, a column isn’t fast enough — call or text 988 (Suicide & Crisis Lifeline) right now.
Anyone using AI for actual research and not just summarizing?
Been using ChatGPT and Claude for a year-ish, mostly for first drafts and brainstorming. Both are fine for that.
What I'm trying to figure out: anyone using AI for *real* research — like working through primary literature on a niche topic, comparing studies, finding the gaps?
I tried it last week with a topic I actually know well to test whether the output was real. The model confidently summarized 3 studies, of which 2 were real and 1 was completely made up — title, authors, journal, all fabricated. Sounded plausible until I tried to find it.
Is there a workflow that gets past this? Or is the answer just "don't use AI for research, use it for writing"?
the made-up study problem is real and it doesn't fully go away even with the better models. what i do:
never let it cite. ever. if i need real sources i pull them myself from pubmed or google scholar then paste the abstracts in and ask the model to compare them. the citations have to come from me, the comparison can come from the model.
also: ask the model what it's *not* sure about. if you ask "what's the strongest critique of X" you get something useful. if you ask "what does the literature say about X" you get hallucinated confidence.
tools are great. the citation hallucination thing is the part that's still embarrassing in 2026.