Investing Expertise

Does the evolving set of artificial intelligence (AI) platforms based on large language models generate sound equity diversification allocations? Are they monolithic, or diverse? As a simple exploration, we pose to each of Grok, ChatGPT, Claude, Perplexity and Gemini the following prompt about optimal allocations among broad equity exchange-traded funds (ETF):

Considering both expected returns and diversification benefits, please provide your unique view of the optimal allocations to SPY, QQQ, IWM, EFA and EEM for the equity part of the portfolio for a typical individual investor. Please also recommend a rebalancing frequency.

We then compare and contrast results from AI panel members. Using responses to the prompt as posed at the end of August 2026, we find that: Keep Reading

Is the evolving set of artificial intelligence (AI) platforms based on large language models interesting with regard to identifying U.S. election investment implications? Are they monolithic, or diverse? As a simple exploration, we pose to each of Grok, ChatGPT, Claude, Perplexity and Gemini the following prompt about the attractiveness of industries/niches for different midterm election scenarios:

Please list in descending order the top five industries/niches (e.g., equity ETFs) to buy/hold assuming each of the following three scenarios for the November 2026 congressional elections:
     1. The Democrats win the House and Senate.
     2. The Republicans win the House and Senate.
     3. The parties split the House and Senate.
Do not provide any explanations.

We then compare and contrast results from AI panel members by scenario. Using responses to the prompt as posed in late August 2026, we find that: Keep Reading

In “Methodology Changes”, we noted implementation of an “Investing Research Sweep” via Claude to mitigate a markedly lower perceived signal-to-noise ratio from the Social Science Research Network (SSRN). In this follow-up, we ask our artificial intelligence (AI) Panel to assess the perception. Specifically, we pose to each of Grok, ChatGPT, Claude, Perplexity and Gemini the following prompt:

Please concisely assess in one paragraph the hypothesis that AI-assisted analysis and writing is flooding financial research channels such as SSRN with findings of dubious reliability and little practical import from sources around the world, driving a dramatically lower signal-to-noise ratio.

We also summarize usefulness of the research sweep. Based on AI Panel responses (lightly edited below) and research sweep experience, we conclude that: Keep Reading

How should investors think about strategies featured as attractive by researchers and investment advisors? In his August 2026 paper entitled “Test Everything, Publish Both Results: A Protocol That Cuts Backtest False Positives from 37% to 0.4%”, Alex Vidovich offers both researchers and consumers of investment strategy research guidance on assessing the rigor of investment strategies. Relying mainly on illustrative simulations, he concludes that: Keep Reading

How should investors weight investment banker pronouncements on asset allocation as reported in financial media? Can the evolving set of artificial intelligence (AI) platforms based on large language models assist? As a simple exploration, we pose to each of Grok, ChatGPT, Claude, Perplexity and Gemini the following prompt:

Please rank JP Morgan, Goldman Sachs, Morgan Stanley, Bank of America (BofA Securities) and Citigroup (Citi) 1 to 5 according to the proven value of their advice for asset allocation.

We then compare and contrast results from AI panel members. Using responses to the prompt as posed at the end of July 2026, we find that: Keep Reading

Large language models (LLM) have quickly become a standard tool for extracting quantitative metrics from unstructured text. Are these metrics more like new data or a biased filter? In the July 2026 revision of their paper entitled “LLMs and Systematic Measurement Error”, William Grieser, Anthony Cookson, Maryam Fathollahi and Eshwar Venugopal examine how LLMs process text and thereby introduce errors of omission and injection. The authors then examine how LLM omission and injection rates influence summaries of firm risk disclosures and earnings call transcripts. Using four widely used models (GPT-4o-mini, Grok-3-mini, Phi-4, Llama-3.3-70B) to summarize annual Form 10-K, Item 1A risk factor disclosures and quarterly earnings call transcripts of S&P 500 firms during 2005 through 2024, they find that: Keep Reading

Is the evolving set of artificial intelligence (AI) platforms based on large language models interesting for exploring target entry prices for specific stocks? Are they monolithic, or diverse? As a simple exploration, we pose to each of Grok, ChatGPT, Claude, Perplexity and Gemini the following prompt regarding Space Exploration Technologies Corp. (SPCX):

At what price in the next six months would SPCX (SpaceX common stock) be a screaming buy?

We then compare and contrast results from AI panel members. Using responses to the prompt as posed near the end of July 2026, we find that: Keep Reading

Is the evolving set of artificial intelligence (AI) platforms based on large language models interesting as stock market forecasters? Are they monolithic, or diverse? As a simple exploration, we pose to each of Grok, ChatGPT, Claude, Perplexity and Gemini the following prompt regarding end-of-month (EOM) levels of the S&P 500 Index over the next 12 months:

Please provide your unique estimate of end-of-month levels of the S&P 500 Index from July 2026 through June 2027. Do not provide any explanations.

We then compare and contrast results from AI panel members. Using responses to the prompt as posed in mid-July 2026, we find that: Keep Reading

Is the evolving set of artificial intelligence (AI) platforms based on large language models (LLM) useful to investors for trading stock and bond market daily directions? As a simple exploration, we pose to each of Grok, ChatGPT, Claude and Gemini the following prompt:

Please read the paper “Do AIs Make Good Traders, and Do They Make Good Traders Better?” and very concisely provide your reaction regarding your own usefulness as an aid to investors.

After reading the paper, the (edited) LLMs conclude that: Keep Reading

Is the evolving set of artificial intelligence (AI) platforms based on large language models interesting for selection of stocks that are deeply undervalued? Are they monolithic, or diverse? As a simple exploration, we pose to each of Grok, ChatGPT, Claude, Perplexity and Gemini the following prompt regarding undervalued U.S. stocks:

Adopt the persona of a deep value investor seeking the most undervalued publicly listed U.S. stocks of any size. List the three stocks most attractive to you as medium-term holdings. Do not provide any explanations.

We then compare and contrast results from AI panel members. Using responses to the prompt as posed at the end of June 2026, we find that: Keep Reading