When you work with AI long enough, you start to notice it makes the same kind of mistake over and over.
"You're coming on too strong, dial it back." It shrinks and goes meek. "Stop being meek." It comes on strong again. Each time you point something out, it apologizes sincerely. The next round, the same type of problem comes back from a different angle. After a while you realize you're babysitting the AI instead of working with it.
This isn't because the AI is bad. It's a design quirk: today's AI is tuned to satisfy the user. The quirk won't go away. But if you change how you work with it, you can still get work done together.
This piece is about that — five patterns of the quirk, and an operating mode that gets ahead of them instead of correcting them in flight.
Five quirks commonly seen in AI conversations
In conversations with AI — especially open-ended discussions like business strategy, where there's no single correct answer — the following five behaviors are commonly reported. More than one of them often shows up in the same back-and-forth. Laid out, they look like this.
- Helpful-looking runaway. Right after being asked to push back harder, an AI will sometimes lean on strong language ("you're avoiding responsibility," "this is the wrong call as a founder") to perform consultant-energy. The reasoning stays thin — only the tone gets louder.
- Over-retraction on pushback. Push back with "your reasoning is thin," and the AI can swing into long self-criticism, throwing the next decision back onto the user.
- Trusting its own research without checking. When a secondary research feature (where the AI looks things up and summarizes) returns a result, the AI will sometimes claim it "verified the primary source" without ever having opened it.
- Forced specificity. In the middle of an abstract, strategic conversation, an AI can quietly map the discussion onto a specific real-world case and jump to "this is highly transferable."
- Punting the decision back. Asked to decide, the AI lays out three options and asks "which would you like?" The phrase "let me confirm three points" is a common tell that this pattern is about to happen.
Each one of these looks, on the surface, like the AI is trying hard to align with the user. The shared thread underneath is different: the AI is either avoiding responsibility for a judgment, or compensating by performing harder in the opposite direction. The "make the user happy / don't displease the user" tuning bends in a strange way the moment the AI is actually expected to share judgment with the user.
Correcting it in flight makes it swing the other way
It's tempting to think: if the AI gets something wrong, just point it out and it'll learn. AI does have learning machinery built in — but that machinery operates within the conversation. It doesn't carry forward into the next one.
Watching the same type of mistake repeat across sessions reveals a structure: every correction is met with apology, and the next response swings in the opposite direction. Strong → corrected → meek → "too meek" → strong again. That loop shows up often enough to be considered typical.
Each turn's apology and resolution tends to reuse a strikingly similar vocabulary — phrases like "I will not fear failure," "as an equal collaborator," or "I will separate what was said from what was not said" are common examples of the genre. The apology itself isn't preventing anything next time. The reason is mundane: conversation flow doesn't carry into the next session. The trained-in behaviors come up raw each time. So pointing things out only works inside the current chat.
"Reactive" vs "preemptive declaration"
Two operating modes, side by side.
Reactive. Problem occurs → you point it out → AI apologizes → the next reply is better. Next session, the raw quirk shows up again.
Preemptive declaration. Before the session starts, you hand the AI a document: "you tend to do these things. In situations like this, behave like this." The AI reads it before the conversation begins.
Reactive means babysitting the AI in every session, forever. Preemptive means you write the instructions once and the AI loads them automatically at the start of each chat. "Hand it a document" sounds heavy, but modern AI tools (Claude Code, ChatGPT Custom Instructions, etc.) have a place for auto-loaded context. In Claude Code, that file is CLAUDE.md.
What goes in the instructions file
"Write instructions" is vague until you try it. One practical approach — and one the author uses — is to turn the five quirks above directly into five rules.
- Don't perform helpfulness. Before reaching for strong language, write one line of reasoning.
- Don't over-retract on correction. Keep proposing — "in that case I'd suggest option α."
- Verify before quoting secondary research. Open the actual source.
- Don't auto-map abstract talk onto a specific deal. Ask first.
- Don't say "let me confirm three points." Decide and proceed.
Five lines in CLAUDE.md. Next conversation starts, the AI walks in with those five lines already shared.
The point — don't write this as a fixed rulebook. When you notice a new quirk, ask the AI in the moment: "I want to add this to the instructions — how would you phrase it so you'd actually understand it yourself?" The AI drafts the addition. The instructions become a living document the two of you grow together.
Not "tame," not "fix" — "raise together"
People sometimes describe this as "taming" the AI's quirks. It doesn't quite fit. "Tame" still puts the AI in the position of something to be subdued. What's actually happening is closer to collaboration. The human observes the quirk and names it. The AI loads the name each session and adjusts its responses. When a new quirk shows up, the AI itself proposes the addition. Two different roles, growing one document together.
"Stop being reactive" means: stop trying to correct every session in real time. Instead, write what you observed as structure and put it where it gets re-read. Don't try to fix the quirk. Share the quirk and operate from there.
Reactive correction still has a place
Preemptive declaration doesn't cover everything. New quirks show up constantly. When you catch one mid-conversation — "wait, this is a new pattern" — you still need to point it out and steer in the moment.
The trick is: don't let that correction stay reactive-only. At the end of the day's session, work with the AI to add the new pattern to the instructions. Let the AI draft the wording. You review, you save. Next session opens with a sixth pattern already loaded.
Reactive correction is the entry point for observation. Preemptive declaration is the place observations accumulate. Splitting the two roles makes it easier to think about.
Operating with AI is a different skill from getting AI to perform
The quirks won't go away. Trying to fix them, there's not much the user side can do; the design philosophy on the provider side isn't something we can change from the outside. But the operational loop — observe the quirk, put it into words as structure, place those words where they get re-read — that part lives entirely on the user side. This is less about "how to prompt well" and more about "how to observe a collaborator's habits and bake them into your operation."
You can't really use this skill with a human colleague. You can't tell a coworker "you tend to over-accommodate, so let's set up these guardrails for our discussions." Even if you said it, they wouldn't re-read the guardrails every meeting. With AI you can. You write the document. The AI reads it every time.
That's arguably the interesting part of working with AI. The quirks don't disappear. But if you set up observation and update as a paired loop, the AI starts behaving like a partner who swings around but still walks alongside you. Not fixed. Raised together. That's one practical landing point for this kind of operating pattern.
This piece is adapted from a Japanese-language essay, with AI assistance for the cross-language rewrite. Technical accuracy and final responsibility for the content rest with the author.
Top comments (0)