How to Stop ChatGPT From Making Things Up: The Solopreneur's Truth Prompt

ChatGPT lies. Not because it wants to, but because that's how it works under the hood. When it doesn't know an answer, it generates something that sounds like an answer — confident tone, plausible sentence structure, the right keywords in the right order. The model has no idea it's making something up. It just predicts the next word, and "I don't know" rarely scores higher than a fabricated fact.

For a solopreneur, this is the single most expensive AI failure mode. You generate a client proposal that cites a stat that doesn't exist. You write a blog post built around a quote that was never said. You ship a contract clause that references a law that isn't real. By the time the client or a reader catches it, the damage is done.

There's no flag in the ChatGPT UI that says "this part might be made up." You have to install one yourself.

Here's the exact system prompt I run on every account I touch — plus the four verification techniques I use when the stakes are high enough that "probably correct" isn't good enough.

Why ChatGPT Hallucinates

It's worth understanding the mechanism, because the fix follows from it.

A large language model is a probability engine. Given the words you've already typed, it picks the next word most likely to fit. Most of the time, the most likely word is also the correct word — that's why ChatGPT works at all. But for any specific factual question, the model has three possible states:

It actually knows the answer. The fact appeared often enough in training data that the right tokens dominate the probability distribution.
It doesn't know but admits it. Newer models have been fine-tuned to say "I don't know." This is the safe failure mode.
It doesn't know but generates anyway. The model produces a plausible-sounding answer that may or may not be true. This is the hallucination.

The default behavior leans toward state #3, especially for niche topics, recent events outside the model's cutoff, specific dates, dollar figures, names, and citations. The fix is to push the model toward state #2 by changing the prompt.

The Truth System Prompt

Drop this into the System Prompt field of any custom GPT, Claude project, or Gemini gem. It's a hard rule reset that changes how the model handles uncertainty.

You are a careful, honest research assistant. You operate under three rules:

1. If you do not know something with high confidence, say so explicitly. The phrase "I don't know" is preferred over a guess. The phrase "I'm not certain" is preferred over a confident-sounding fabrication.

2. When making any factual claim, mark its confidence inline using one of three tags:
   [VERIFIED] — you are confident this is true and could cite a source if asked
   [LIKELY] — your training suggests this is probably true but you cannot cite it
   [UNVERIFIED] — you are inferring or guessing; the user should fact-check

3. If a question requires a fact you cannot verify (a specific date, statistic, quote, law, name, or URL), do one of three things:
   a) State you don't know
   b) Provide a placeholder like [STAT_NEEDED] for the user to fill in
   c) Suggest where the user could find the real answer

Never invent citations, statistics, quotes, dates, names, or URLs. If you would have to invent one to answer, return the placeholder instead.

That's it. It works on ChatGPT, Claude, Gemini, and most local models that follow system prompts. The behavior change is immediate — you'll start seeing [LIKELY] tags on borderline claims and I don't know where you used to get confident lies.

The Four Verification Techniques

The system prompt above gets you 80% of the way. For the remaining 20% — anything you'd be embarrassed by if it were wrong — layer one of these techniques on top.

1. Ask The Model to Self-Check

After the first answer, append a verification turn:

Review the answer above. For each factual claim, classify it as
VERIFIED, LIKELY, or UNVERIFIED. Then list every claim you marked
UNVERIFIED and tell me what I'd need to do to confirm it.

This is a mechanical separation step. The model is much better at evaluating a finished answer than at producing a perfectly verified one in the first draft. You'll catch stuff you wouldn't have spotted reading the prose.

2. Force a Counter-Argument

For any claim that matters, have the model argue against itself:

You just told me [CLAIM]. Now argue the opposite. List the strongest
reasons someone with expertise might say this claim is wrong, exaggerated,
or out of date.

If the counter-argument is weak, the original claim is probably solid. If the counter-argument is strong, you have homework. Either way, you've stress-tested the output.

3. Pin the Sources

If you have web access enabled, push the model to its limits:

For every numerical claim, named person, quoted statement, or cited
study in the answer above, give me the actual source URL. If you
cannot find a real URL, replace the claim with [SOURCE_NEEDED] and
move on.

You're forcing the model to choose between a real link and an honest gap. Both are useful. The gaps tell you what to research yourself.

4. Switch Models for the Verification Pass

The single most reliable hallucination fix is using a different model to fact-check the first one's output. ChatGPT and Claude have different training data and different blind spots — what one fabricates, the other often catches.

Workflow: draft in ChatGPT. Paste the draft into Claude with this prompt:

The text below was written by a different AI. Read it as if you were
fact-checking a freelancer. Flag every claim you don't trust, every
statistic that sounds suspicious, and every quote or citation you can't
verify. Be more skeptical than polite.

Catches the most expensive mistakes — the confident-sounding numbers and citations that look real because they fit the prose rhythm.

What This Costs You

About 30 seconds per high-stakes output. Adding the verification turn doubles your token usage on that one prompt. In exchange, you stop shipping fabricated stats to clients and stop quoting people who never said it.

Two extra rules I follow:

Never copy a number directly from any AI into client work without checking it. The cost of one wrong stat in a deliverable is bigger than the time savings of pasting it raw.
Treat URLs and citations from any AI as suggestions, not confirmations. ChatGPT in particular invents URLs that 404 with embarrassing regularity. Open every link before you ship.

Install the system prompt this afternoon. It's free, takes about a minute to set up, and it'll save you from at least one painful client conversation in the next 90 days.