The new experiment: What is the probability of the US Steel/Nippon Steel merger being officially announced before January 21, 2025?
For the first time, today Jeremy is unveiling the raw output of what used to be called Old Bot, now called “Multi-AI Oracle.” Bottom line: 22%.
===============================
Welcome to the Multi-AI Oracle.
===============================
What is your question? What is the probability of the US Steel/Nippon Steel merger being officially announced before January 21, 2025?
Do you have any other information you wish to pass along to assist in answering? (Hit Enter to skip)
ID: N/A
Question: What is the probability of the US Steel/Nippon Steel merger being officially announced before January 21, 2025?
Obtaining outside newsfeed.
Summarizing outside newsfeed.
Querying Perplexity (AI predicts: 0.2 – confidence: 6)
Querying Claude (AI predicts: 0.2 – confidence: 5)
Querying Mistral (AI predicts: 0.2 – confidence: 6)
Querying Cohere (AI predicts: 0 – confidence: 7)
Querying OpenAI (AI predicts: 0.15 – confidence: 5)
Median from LLMs: 0.2
Base rate: 0.15 (from OpenAI)
SD: 0.08
Confidence: 6
Mellers: 0.08
Reverse Mellers: 0.33
Beta Distribution: 0.23
# LLM responses: 5
We queried Perplexity, Claude, Mistral, Cohere, OpenAI.
A summary of what the responding AIs considered is as follows:
The proposed merger between US Steel and Nippon Steel faces significant uncertainty due to opposition from the United Steelworkers union, national security concerns, and the need for approval from the Committee on Foreign Investment in the United States (CFIUS). The US National Security Panel has granted an extension for resubmission until after the presidential election on November 5, 2024, which analysts suggest makes approval before January 21, 2025, improbable. The complexity of the deal and political sensitivity further complicate the timeline for potential approval.
Runtime: 63 seconds.
Background:
Jeremy Lichtman has been coding updates to Old Bot, now named the Multi-AI Oracle as he explores ways to teach AIs to become better forecasters, perhaps someday, better than our human team of Brian LaBatte and Carolyn Meinel, both of whom are “superforecasters™.”
Jeremy’s bestworldbot:
Through June 2025, Jeremy plans on continuing to field another of his creations, bestworldbot, on the next quarter beginning Oct. 1, 2024, of the current Q3 AI Forecasting Benchmark Tournament. Below is its leaderboard of Sept. 23, 2024. Bestworldbot is #46 out of 52 competitors. A likely explanation for bestworldbot’s declining status is that we tried extremizing bestworldbot’s forecasts. With most human forecasters, extremizing is, on average, effective. However, we now have concluded that extremizing makes bestworldbot worse.
The Human Team
BestWorld’s staff of Brian LaBatte and Carolyn Meinel had been competing with Botmaster Jeremy Lichtman’s Mult-AI Panel on our forecasting question of “What is the probability that the US Federal Reserve Board will cut interest rates in September 2024?” We now have the answer: Sept. 18, 2024, the US FED lowered its key overnight borrowing rate by a half percentage point, or 50 basis points, a huge cut compared to the usual quarter point changes, and the first cut since 2020. Later we’ll post our scores. The final scores will not be what we forecasted just before the answer was known, because being more correct — or incorrect — earlier will count toward the final scores.
Summary of all our FED rate forecasts: We stopped reporting the Multi-AI Panel on Sept. 13. Its final answer was 85%, up from the previous day’s 75%. As of Sept. 18, Old Bot had dropped from 85% to just 55%. Our staffers remained at 84% median, 95% with extremizing via one of Prof. Barbara Meller’s algorithms. This includes the effect of our earlier, lower forecasts. Our finl spot forecast was 98% for Brian, 99% for Carolyn.
Our FED rate forecast staff forecasts are below. Note that our spreadsheet also included some of our bots.
The currently retired Multi-AI Panel
There were five generative AIs on the Multi-AI Panel: Perplexity, Claude, Mistral, Cohere, and OpenAI. They forecasted just one question: “What is the probability that the US Federal Reserve Board will cut interest rates in September 2024?” The answer: Yes.
.
Jeremy’s previous Bots vs Staff forecasts:
Sept. 23, 2024
Sept. 18, 2024
Sept. 17, 2024
Sept. 16, 2024
Sept. 13, 2024
Sept. 12, 2024
Sept. 11, 2024
Sept. 10, 2024
Sept. 9, 2024
Sept. 6, 2024
Sept. 5, 2024
Sept. 4, 2024
Sept. 3, 2024
Sept. 2, 2024
Aug. 30, 2024
Aug. 29, 2024
Aug. 28, 2024
Aug. 27, 2024
Aug. 26, 2024
Aug. 23, 2024
Aug. 22, 2024
Aug. 21, 2024
Aug. 20, 2024
Aug. 19, 2024
Aug. 16, 2024
Aug. 15, 2024
Aug. 14, 2024
Aug. 13, 2024
Aug. 12, 2024
Aug. 9, 2024
Aug. 8, 2024
Aug. 7, 2024
Aug. 6, 2024
Aug. 5. 2024
Aug. 2, 2024
Aug. 1, 2024
July 31, 2024
July 30, 2024
July 29, 2024
July 26, 2024
July 25, 2024
