A while back I was researching a topic I didn't know much about — the kind of casual, late-night "let me just ask the AI a few questions" session. A few messages in, I asked a follow-up that only made sense in the context of what we'd just been talking about. I didn't restate the subject, because... why would I? We were three messages into the same conversation.
The answer came back completely off-topic. It had lost track of what "it" referred to, latched onto the wrong noun, and confidently explained something I hadn't asked about at all. Not a small tangent — a whole paragraph about the wrong thing.
My first reaction was annoyance at the model. My second, more useful reaction came a bit later: I'd been treating it like a person who remembers what we were just discussing and fills in the gaps naturally. It doesn't do that the way a human conversation partner does. If I don't restate the subject, it's genuinely not there for the model — it's not being lazy, there's just nothing to work with.
So I started over-specifying. Every follow-up got longer: restate the subject, restate what I actually wanted, restate the constraint I cared about. It worked, but some days I didn't have the energy for it — I'd just take the mediocre answer, say "ok thanks," and move on. Which meant I was quietly leaving useful answers on the table half the time, just because typing out the full context felt like a chore.
Eventually I stopped thinking of it as "the AI being difficult" and started treating it as a simple rule: if I want it to know something, I have to say it. It won't infer the unstated stuff the way a person would, no matter how obvious it feels to me.
Once that clicked, a few concrete habits followed.
Restate the subject, every time
Not "what about the second one" — the actual name of the thing. It costs three words and removes an entire failure mode.
Say what you actually want, not just the topic
"Tell me about X" and "I'm trying to decide whether X is worth the switching cost, tell me about X" produce different answers. The second one tells the model what to optimize the answer for. Without it, you get the generic version — technically about the right topic, but not shaped for your actual question.
Give it the constraint you care about
If budget, time, or a specific tradeoff matters to your decision, say so directly. It won't guess that you're price-sensitive, or that you already tried the obvious thing and it didn't work. That context lives in your head, not in the words on screen — unless you put it there.
Ask for the shape you want the answer in
If you want a short answer, say short. If you want a list you can act on, say that. Left unspecified, you get a default-length paragraph that's rarely the format you actually needed.
Give an example when "good" is hard to describe
Words like "casual" or "detailed" mean different things to different people. If you have something close to what you want — even a sentence — pasting it in as a reference does more than describing the vibe in adjectives.
The actual lesson
None of this is a trick. It's just accepting that a model doesn't share the context sitting in my head, and won't reach for it unless I hand it over — even the parts that feel too obvious to mention. The habit that actually fixed my "generic answers" problem wasn't a clever phrase, it was just: stop assuming it remembers or infers what I mean, and say it anyway.
Still working on doing this consistently when I'm tired and just want a quick answer. Curious whether other people have found a shortcut for that part, or if it's just discipline.
Top comments (0)