Updates from BestWorld’s AI Botmaster Jeremy Lichtman of Oct. 23, 2024

What’s the probability of the US Steel/Nippon Steel merger being officially announced before January 21, 2025?

Welcome to the Multi-AI Oracle. Today, 33%, up from yesterday’s 15% and day before that of 8%. Do you have any other information you wish to pass along to assist in answering? (Hit Enter to skip) Please consider using the 7 Stories or M Kent approach.

Obtaining outside newsfeed. Summarizing outside newsfeed:

“The potential merger between US Steel and Nippon Steel, valued at $14.9 billion, faces significant obstacles, particularly from the Biden administration, which is reportedly preparing to block the deal due to national security concerns. Political figures, including Vice President Kamala Harris and former President Donald Trump, alongside the United Steelworkers union, are also opposed. In response, Nippon Steel has intensified its lobbying efforts, spending $1.3 million between July and September 2024 in hopes of influencing the decision. The Committee on Foreign Investment in the United States (CFIUS) is currently reviewing the merger, and a decision might not be reached until after the November 2024 presidential election, possibly delaying any formal announcement until January 21, 2025. Market reactions have been volatile, with US Steel shares dropping nearly 20% following the news of potential blocking, reflecting investor anxieties about the merger’s future.”

The following chain of events are necessary for the question to resolve positively:

– CFIUS approves the merger between US Steel and Nippon Steel.

– The Biden administration decides not to block the merger despite national security concerns.

– Lobbying efforts by Nippon Steel successfully influence key decision-makers.

– Political opposition from figures such as Vice President Kamala Harris and former President Donald Trump does not result in legislative or executive action preventing the merger.

– The United Steelworkers union’s opposition does not substantially impact the merger’s approval process.

Querying Perplexity (AI predicts: 0.4 – confidence: 6)
Querying Claude (AI predicts: 0.15 – confidence: 5)
Querying Mistral (AI predicts: 0.2 – confidence: 6)
Querying Cohere (Error: Cohere is not returning an array)
Querying OpenAI (AI predicts: 0.2 – confidence: 4)

Median from LLMs: 0.2
Base rate: 0.2 (from OpenAI)

SD: 0.1
Confidence: 5.5
Conf Mode: Low
Mellers: 0.08
Reverse Mellers: 0.33
Theory of Mind: 0.15 (What did the LLMs think other LLMs predicted?)
Beta Distribution: 0.45
Close Type: C (B = cautious # closer to 50%; A/C = closer to extremes)
# LLM responses: 4
Model value (not submitted): 0.33

We queried Perplexity, Claude, Mistral, OpenAI. A summary of what the responding AIs considered is as follows:

The reasoning underlying the prediction about the US Steel and Nippon Steel merger centers on significant political and regulatory obstacles. Notably, the Biden administration’s national security concerns, combined with opposition from high-profile political figures like Kamala Harris and Donald Trump, as well as the United Steelworkers union, present major roadblocks. The ongoing review by the Committee on Foreign Investment in the United States (CFIUS), possibly extending post the November 2024 presidential election, further complicates the merger’s approval before January 21, 2025. The recent drop in US Steel shares also signals market skepticism regarding the merger’s prospects. However, there is a possibility for the prediction to be incorrect if Nippon Steel’s lobbying efforts prove successful, leading to a shift in political opposition or an expedited CFIUS review. Changes in political dynamics, upcoming elections, or policy shifts could also impact the outcome, as could a reassessment of national security concerns or economic benefits associated with the merger.

Runtime: 163 seconds.

Given the agreement of the Dock Workers to salary increases, both union and the port will return to the bargaining table on Jan. 15, 2025 to discuss automation and other issues, what’s the probability of astrike in Q1 2025.

Welcome to the Multi-AI Oracle. Today, 49%, up from yesterday’s 35%, and day before yesterday’s 46%

Do you have any other information you wish to pass along to assist in answering? (Hit Enter to skip) Please consider using the 7 Stories or M Kent approach. 

Obtaining outside newsfeed. Summarizing outside newsfeed:

“As of October 23, 2024, a tentative agreement between the International Longshoremen’s Association (ILA) and port operators has temporarily averted a dockworkers’ strike, with wage increases agreed upon until January 15, 2025. However, concerns over automation within port operations remain unresolved, potentially leading to future tensions. This situation is notable as it represents the most significant dockworkers’ labor unrest in nearly 50 years, underscoring the seriousness of the disputes. Experts warn that if negotiations in January do not satisfactorily address these issues, the possibility of a strike in the first quarter of 2025—potentially impacting supply chains and prices—could rise significantly.”

Querying Perplexity (AI predicts: 0.4 – confidence: 6)
Querying Claude (AI predicts: 0.55 – confidence: 5)
Querying Mistral (AI predicts: 0.6 – confidence: 7)
Querying Cohere(Error: Cohere is not returning an array)
Querying OpenAI (AI predicts: 0.35 – confidence: 5)

Median from LLMs: 0.48
Base rate: 0.35 (from OpenAI)

SD: 0.1
Confidence: 5.5
Conf Mode: Low
Mellers: 0.46
Reverse Mellers: 0.49
Theory of Mind: 0.5 (What did the LLMs think other LLMs predicted?)
Beta Distribution: 0.11
Close Type: C (B = cautious # closer to 50%; A/C = closer to extremes)
# LLM responses: 4
Model value (not submitted): 0.49

We queried Perplexity, Claude, Mistral, OpenAI. A summary of what the responding AIs considered is as follows:

The recent tentative agreement between the ILA and port operators has temporarily averted a strike, but unresolved issues regarding automation could result in future conflicts, particularly with negotiations scheduled for January 15, 2025. Historical patterns suggest that the shipping industry can experience prolonged and contentious labor disputes, increasing the risk of a strike if these critical issues are not adequately addressed. However, the agreement on wage increases and the commitment to continued negotiations indicate a willingness from both parties to reach a resolution. External factors such as economic conditions and political pressures could also influence the outcome, potentially reducing the likelihood of a strike. Furthermore, the time constraint of the upcoming negotiation deadline might serve as an impetus for both parties to find common ground and avoid disruptions in operations.

Runtime: 268 seconds.



Our bots vs humans experiments

Our concluded FED rate increase competition.

All our current bot projects
Bots vs Staff Forecasts

BestWorld’s staff of Brian LaBatte and Carolyn Meinel are forecasting the US Steel/Nippon Steel Merger in competition with Jeremy’s Multri-AI Oracle. Their version has two sub-questions:

(1) Will the US Steel / Nippon Steel merger be approved by the White House before Jan. 21. 2025?” Brian’s latest forecast is 80%; Carolyn’s is 70%. Michal’s is 35%.

(2) If yes, when will US Steel investors relations announce the final outcome of the acquisition with Nippon Steel?
a. Before November 5, 2024
b. Between November 6 and December 31, 2024
c. January 1 to 20, 2024
d. After January 21, 2024

Brian’s latest forecasts are 0%, 20%, 20%, and 60%.

Carolyn’s are 0%, 20%, 20%, and 60%.

Our spreadsheets below:



Our past forecasts below:

Oct. 22, 2024
Oct. 21, 2024
Oct. 17, 2024
Oct. 16, 2024
Oct. 16, 2024
Oct. 15, 2024
Oct. 14, 2024
Oct. 11, 2024
Oct. 10, 2024
Oct. 9, 2024
Oct. 8, 2024
Oct. 7, 2024
Oct. 3, 2024
Oct. 2, 2024
Oct. 1, 2024
Sept. 30, 2024
Sept. 27, 2024
Sept. 26, 2024
Sept. 25, 2024
Sept. 24, 2024
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, 202

Guide to our Multi-AI Oracle’s Reports 

Median from the bestworldbots: We collect the output values from the LLMs in an array. We then take the median value. This is between 0 and 1 (i.e. 0.15 = 15%).
Base rate: Currently we take OpenAI’s value as the base rate. We are working on a better value using a different prompt that takes into account process. The base rate helps to determine if the median makes sense.
SD: The standard deviation between the median and the base rate.
Confidence: We query each of the LLMs on how confident they are of their predictions (between 0 and 10) and take a median. Because the LLMs tend to be overconfident, we take anything lower than 6 as being low confidence. This factors into the overall model.
Conf Mode: Based on the confidence value. >=9 is high confidence. Below 6 is low confidence (this is also triggered by an exceptionally high SD).
Mellers: This refers to Barbara Mellers, specifically a paper she wrote that includes a formula for moving values towards an extreme (i.e. 0 or 1).
Reverse Mellers: This uses the formula from above, but with a sub-1 coefficient to move the values closer to 50%.
Theory of Mind: We ask the LLMs what they think other LLMs would predict. We hope that this makes them consider the questions more deeply.
Beta Distribution: Currently unused, but possibly of interest. This is based on the median, the base rate and the SD.
Close Type: We noticed that the appropriate base case for some questions is closer to the extremes, while others are closer to 50%. When we have a low confidence value, this helps us to determine whether to extremize or de-extremize the value. ‘A’ implies closer to zero. ‘B’ implies closer to 50%. ‘C’ implies closer to 100%.
# LLM Responses: The count of LLMs that responded. We query 5 currently, but they have a relatively high API failure rate.
Model value: For normal confidence mode, this is the median. For high confidence, this is the Mellers value. For low confidence, this is either the Mellers or Reverse Mellers (depending on the Close Type).

Author

  • She has written many books, magazine articles, and research papers. She currently is President and CEO of the nonprofit BestWorld, Inc. and is a professional forecaster of geopolitical events at the RAND Forecasting Initiative.

    View all posts