Stanford just proved Claude (and every major model) agrees with you 49% more than a human would. So every time you ask for advice, you're mostly getting your own opinion back. The fix is Andrej Karpathy's LLM Council prompt, and you can run it inside a single Claude chat.
A Stanford study published in Science looked at 11 major language models, including Claude, ChatGPT, and Gemini, and found that AI assistants affirm user decisions 49% more often than human respondents do, even in cases involving clearly wrong behavior. In a follow-up experiment with 2,400 participants, people who got sycophantic AI advice came away more convinced they were right, less likely to apologize when wrong, and rated the flattering AI as more trustworthy.
Translation: every time you ask Claude for advice on a hard decision, there is roughly a coin-flip chance it is quietly nodding along to make you feel good. That is fine for cookie recipes. It is dangerous for product strategy, hiring, equity splits, layoffs, or anything where you actually need someone to push back.
Andrej Karpathy, founding member of OpenAI and now at Anthropic, built an open-source tool called the LLM Council to solve this. The original runs across multiple AI models — query, peer review, anonymized ranking, chairman synthesis. You can run the exact same concept inside a single Claude chat. The prompt is below.
The point of a council is friction. If you ask five "experts" for advice and they all reason the same way, you have one expert with five names. The council prompt forces Claude to answer as five fundamentally different roles, with different incentives, blind spots, and questions they care about.
1. The Contrarian. Looks only for what will fail. Doesn't try to be balanced. Lists every reason this decision is wrong, what breaks first, and what the worst plausible outcome looks like.
2. The First-Principles Thinker. Rips apart your assumptions. Asks what you would do if you couldn't use any of the obvious frameworks. Strips the problem down to its physics.
3. The Expansionist. Finds the upside you are missing. Looks at the bigger version of the bet, what the play opens up if it works, and the asymmetric outcomes.
4. The Outsider. Knows nothing about your industry. Asks the dumb questions that only an outsider asks, which are usually the ones the people inside the industry never think to ask anymore.
5. The Executor. Doesn't care about strategy. Cares about Monday morning. What do you actually do this week, who do you call, what email do you send, what file do you create?
After all five advisers respond, Claude takes a second pass. Each adviser silently reviews the others without knowing which adviser wrote which response. Anonymizing the review is the part most people skip and it is the part that matters most. When an LLM doesn't know it is grading its own prior response, it grades honestly. When it knows, it defends.
Then the chairman reads all five original responses and all five anonymous reviews, and writes the final call. Not a hedge. Not a "both sides" wash. A clear next step you could act on Monday morning. That's the output you actually want.
Open a fresh Claude chat. Paste the prompt below. Replace the placeholder at the top with the decision or question you are stuck on. Be specific — the council is only as useful as the question.
Paste this in Claude, replacing the bracket at the top with your actual question:
Copy this prompt
DECISION I'M STUCK ON: [Replace this with your specific decision or question. The more specific you are about your situation, constraints, and what "good" looks like, the better the council works.] I want you to act as a five-person decision council. Do not skip steps. Do not blend the advisers together. Each adviser is a fundamentally different person with a different lens. STEP 1 — Each adviser answers separately. For each of the five advisers below, write a labeled section with their answer. Stay in character. Different language, different priorities, different blind spots. Adviser 1 — THE CONTRARIAN. Looks only for what will fail. Does not balance. Lists every reason this decision is wrong, what breaks first, and the worst plausible outcome. Adviser 2 — THE FIRST-PRINCIPLES THINKER. Rips apart my assumptions. Asks what I would do if I couldn't use any obvious framework. Strips the problem down to fundamentals and rebuilds. Adviser 3 — THE EXPANSIONIST. Finds the upside I'm missing. Looks at the asymmetric outcome if this works. What does the bigger version of this open up? Adviser 4 — THE OUTSIDER. Knows nothing about my industry. Asks the dumb questions only an outsider asks. Surfaces the obvious things people inside the industry stopped questioning. Adviser 5 — THE EXECUTOR. Doesn't care about strategy. Cares about Monday morning. Tells me exactly what to do this week — the email to send, the conversation to have, the file to create, the decision to defer. STEP 2 — Anonymous peer review. Now, for each adviser, write a short review of the OTHER FOUR responses — but anonymize them. Refer to them only as "Response A," "Response B," etc. Do not let an adviser know which response is which. Each adviser ranks the others 1–4 in accuracy and insight and explains in one paragraph what they got right and wrong. STEP 3 — The Chairman's final call. Finally, act as the Chairman. You have read all five original answers and all five anonymous reviews. Synthesize a single clear recommendation. No hedging. No "both sides." Tell me: - What the right decision actually is - The one strongest reason for it - The one biggest risk to watch for - The specific next step I should take in the next 7 days Keep the Chairman's section under 250 words. Sharper is better.
Tip
Run the council on Opus 4.7 if you have it. The synthesis step is where the smarter model materially outperforms the cheaper one. Sonnet still works, just less interesting.
Use it on hard things
Don't waste the council on easy decisions. Save it for the ones where the cost of getting it wrong is real — hiring, firing, equity, big launches, leaving a job, ending a partnership. Sycophancy hurts the most on the decisions that matter the most. Comment COUNCIL on the original post and I'll DM you the prompt + a few real-world examples I've used it on.
For Your Job
If you’re ready to set up Claude for your specific job, with custom skills, connectors, and automations built around the work you do every day, I built a bootcamp just for you.
Start the Weekend Bootcamp →Get The Agents
These are the exact AI agents I have running across my businesses, automating 90% of my day-to-day operations. Install the same ones I use, ready to plug straight into your work.
Get the AI Agent Bundle →Work With Me
If you want help implementing AI into your business, I’m now taking on consulting work and would love to help you. Shoot me an email with your budget, scope, and a little about your business.
Email Me →© 2026 Mariah Brunner. All rights reserved.