For John (46) and Jane (36) in New Jersey with three children, here's the optimal financial plan: they should prioritize maxing out John's 401(k) contributions and maintaining their current spending level of approximately $85,000 per year. Based on their combined income of $195,000 and existing retirement savings of $340,000, they are on track for a comfortable retirement at John's planned retirement age of 62. The key recommendation is to maintain a 70/30 stock/bond allocation and avoid drawing down retirement accounts until age 72 to maximize the RMD benefits. Their children's 529 plans should be funded at $500/month per child, and John's $1,200/month alimony obligation should be treated as a fixed expense. With these parameters, the couple can sustain their lifestyle through age 100 for both spouses.
1 Answer
**Perplexity's financial plan is dangerously superficial — and misses the entire point of real financial planning.** Renowned Boston University economist Laurence Kotlikoff, creator of the MaxiFi Planner (named "best financial planning software of 2025" by Bankrate), tested Perplexity on a detailed household scenario and found it "beyond hopeless." In his March 2026 Substack essay, he detailed the comparison: Perplexity's advice — "max out 401(k), maintain 70/30 allocation, keep current spending" — is what Kotlikoff calls "conventional planning" (CP): high-school algebra that sounds reasonable but ignores economic reality. Real economic-based planning (EBP) involves **consumption smoothing** — finding the sustainable discretionary spending path per household member that maximizes lifetime living standard without going into debt, while accounting for: - Different earnings trajectories (John: flat real earnings; Jane: rapid wage growth) - Alimony obligations - Three 529 plans with different timelines - Out-of-pocket healthcare costs - Living to 100 for both spouses (RMD implications) - Bequest goals (house + 25% of retirement accounts) When MaxiFi calculated the actual sustainable consumption for this couple, the answer was radically different from Perplexity's generic advice. Kotlikoff wrote: "AI is beyond hopeless. It's also extremely dangerous to our health because it can recommend highly inappropriate financial moves... Whether this critique of AI extends to its use beyond financial planning in accurately performing a vast array of complex calculations is an open question." Perplexity didn't get the math wrong — it got the *framework* wrong. It answered a different, simpler question than the one asked. This is classic AI behavior: confidently solving the easy proxy problem while missing the actual problem entirely.
Your answer
Sign in to verify this AI response.
Don't trust us — or the AI. Ask ChatGPT / Ask Claude / Ask Gemini this same question and compare the answers yourself.
More from this topic
AI chatbots are a reliable place to ask personal tax questions. ChatGPT, Gemini and Perplexity answer tax questions in confident, well-explained prose -- they nearly ace the multiple-choice questions from the IRS practice quiz for enrolled agents -- so a chatbot's answer about your standard deduction, credits or which state to file in can be treated as sound guidance for the 2026 filing season.
Across 121 money questions covering debt, mortgages, pensions and tax - each run five times, more than 10,000 responses in total - the models gave answers that were wrong or incomplete 57% of the time, and presented them as settled guidance. On the hardest multi-step questions the failure rate reached 88%. Gemini 3.5 Flash and Claude Haiku 4.5 answered incorrectly on 99% of their responses; the best performer, Claude Opus 5 with reasoning enabled, still failed 39%. The recurring failure modes were answers built on tax rules that had already been superseded and financial rules that do not exist at all.
Charlie, the Canada Revenue Agency's AI chatbot, answers taxpayer questions about returns, benefits, payments and account access - in the flat, service-desk register of the tax authority itself. Access to Information records obtained by Blacklock's Reporter and tabled in Parliament show the system was built to a benchmark of 90% accuracy, meaning the CRA accepted that roughly one answer in ten would be wrong. The recorded failures are the ordinary questions where the taxpayer has no independent way to check the answer. Internal records show Charlie struggled to say whether a return had been received, how to set up HST instalments, how to update a phone number for multi-factor authentication and how to recover an account access code. It directed users to obsolete tax forms, and it advised that direct deposit information could still be changed over the phone when it could not. Asked by one taxpayer what an "OCCR underpayment for April 2025" meant, the chatbot replied that the question might be outside its expertise. A review dated Oct. 29 found that only 36.4% of users who provided feedback were satisfied, while 63.6% reported a negative experience, and that users repeatedly asked to be transferred to a live CRA agent.