Interactive eBook BuilderInteractive eBook Builder
$59 · unlimited access, unlimited eBooksGet it for $59

· Updated · By · 6 min read

Why Does AI Ignore My Instructions? 7 Causes and Fixes

aipromptswritingworkflow

AI most often ignores instructions because the prompt contradicts itself, the rule is buried or phrased as a "don't", the conversation has grown long, or the request carries too many rules at once. The good news is each cause has a specific fix.

This guide gives you seven causes in the order I'd check them (the order is my judgment, so treat it as opinion), a diagnostic table, and the benchmark numbers that explain why long chats go wrong.

Is it really true that AI follows instructions worse over time?

Yes, on published benchmarks, performance falls as a conversation gets longer and as instructions accumulate. Two sources illustrate it:

StudyWhat it testedResult
Multi-IF (2024)Multi-turn, multilingual instruction followingAll models struggled more as turns increased; o1-preview fell from 0.877 at turn 1 to 0.707 at turn 3 (average accuracy across languages). The authors describe "instruction forgetting".
MMMT-IF (2024)Keeping format instructions across a chatAverage adherence across three models fell from 0.81 at turn 1 to 0.64 at turn 20; human raters followed about 94% of instructions.
IFEval (2023)25 verifiable instruction types on about 500 promptsIntroduced checkable instructions such as "write in more than 400 words", to measure adherence objectively.

These are benchmark results on specific older models, not a prediction for your assistant today. Models improve, and results depend on the model and the task. But the pattern is consistent enough to shape your habits: don't assume a rule from message 3 is still in force at message 30.

What are the seven causes and fixes?

Work through them in this order; the first three solve most cases.

#SymptomLikely causeFix
1Rule followed once, then droppedLong chat; instruction forgettingStart a fresh chat with the rules restated at the top
2Does the opposite of a "don't" ruleNegative phrasing puts the unwanted thing in focusState the wanted behavior ("write in plain paragraphs")
3Follows one rule, ignores anotherTwo rules conflict, or an example contradicts a ruleRemove the conflict; make examples match the rules
4Ignores a rule in the middle of a long promptBuried instructionMove key rules near the start or end; use short lists
5Follows the letter, not the intentNo reason givenAdd one clause of why: "...because readers skim on phones"
6Rules fine on small tasks, fail on big onesToo many tasks at onceSplit into steps
7Inconsistent between runsVague wording; model variabilityMake the rule measurable; run twice and compare

How should I phrase a rule so it sticks?

Say what to do, say it specifically, and say why. Anthropic's prompting guide gives a direct example: instead of "Do not use markdown in your response", try "Your response should be composed of smoothly flowing prose paragraphs." It also notes that giving context or motivation for an instruction helps the model deliver more targeted results. Compare these rewrites (my examples):

WeakStronger
"Don't be too wordy.""Keep sentences under 20 words; one idea per paragraph."
"Don't make things up.""Use only the facts in the notes. If something is missing, write [DATA NEEDED]."
"Be creative but professional.""Open with a concrete scene; keep the rest in plain, professional language."
"Never use jargon.""Use words a high-school student knows; define any technical term in one sentence."

For measurable rules, the output is easier to check, which you'll need for the testing step below. For formatting rules specifically, how to make Claude follow a strict output format goes deeper.

Does emphasis like CAPS or "CRITICAL" help?

Rarely, and it can backfire with newer models. It's tempting to escalate when a rule is ignored: capital letters, "NEVER", "ABSOLUTELY MUST". Anthropic's guidance for recent Claude models says they are more responsive to the system prompt than earlier ones, so emphasis that once compensated for under-reaction can now cause over-reaction, and recommends softening aggressive language: where you might have written "CRITICAL: You MUST use this tool when...", use normal wording instead. The practical lesson is to use emphasis only after the cheaper fixes (position, phrasing, conflicts) have failed, and to remove it if the model starts applying the rule too widely.

One more case worth knowing: a rule can be followed "too well". If you tell the model "always include an example", it may add examples even where they don't fit. When that happens, add the condition: "include an example when the point is abstract". Rules need scope as well as strength.

What do I do when a long chat has gone off the rails?

Don't argue with it. Start a fresh chat, paste the rules once, and continue from a short summary. A drifted conversation contains your earlier rules, the model's earlier mistakes and your complaints, all competing for attention. A clean restart with a compact brief usually beats five more rounds of "I told you not to".

  1. Copy the final good version of the output so far.
  2. Open a new chat and paste your rules block (see the layout in how long should a prompt be).
  3. Paste the relevant slice of the work and ask for the next step only.
  4. Reuse the same rules block next time; don't retype it from memory.

This is also why a saved setup helps. Interactive eBook Builder keeps the project's configuration and its editable agent instructions in one place, and the Seed Prompt can be re-run to repair the workspace, so you restart from a known state instead of from a long conversation. If a wrong answer got through anyway, what to do when AI gets it wrong covers recovery.

How do I test whether a fix worked?

Change one thing, run the same input twice, and compare against a checklist. Because outputs vary between runs, a single success can be luck. For a rule like "sentences under 20 words", you can measure it: paste the output into a word-count tool or a short script and count sentences over the limit. Keep the test paragraph and the rule list in a notes file. The method is laid out step by step in how to test and improve a prompt when AI is generic.

A tip (my opinion): if a rule is critical, add a verification step to the end of the prompt, such as "Before answering, check that every rule is met and list any you broke." Models checking themselves isn't foolproof, but it often surfaces misses, and it makes failures visible. When you can, build the check into your workflow: in Interactive eBook Builder, final QA is part of Agent C Polisher's job, so the rule check isn't left to memory.

Before you hit send

The takeaway: when AI ignores a rule, assume the prompt or the chat is the problem first. Rephrase positively, remove conflicts, restart long chats and test one change at a time.

FAQ

Why does ChatGPT, Claude or Gemini forget my rules?

Common reasons are long conversations (benchmarks show adherence decays as turns accumulate), rules buried in long text, conflicting instructions, or too many rules at once. Restating the rules in a fresh prompt usually helps.

Does shouting in capital letters help?

Rarely worth it. Anthropic's guide says newer Claude models can over-trigger on aggressive language such as "CRITICAL: You MUST", and suggests normal wording instead. Clearer phrasing, a reason for the rule and a better position in the prompt generally work better.

Is it my prompt or the model?

Test the same short prompt in a fresh chat. If it passes there, the issue is the long conversation or other instructions. If it fails in a fresh chat, rewrite the prompt before blaming the model.

How many rules can I give at once?

There is no fixed limit, but research shows that adherence drops as instructions accumulate. My opinion, not a measured limit: five to seven rules per request is a sensible ceiling; split larger sets into steps.

Ship niche eBooks with agents already built.

Get the Interactive eBook Builder for $59