Updates from BestWorld’s AI Botmaster Jeremy Lichtman of Oct. 22, 2024

Given the agreement of the Dock Workers to salary increases, what’s the probability of a strike in Q1 2025?


Welcome to the Multi-AI Oracle. Today, 35%, down from yesterday’s 46%

Obtaining outside newsfeed. Summarizing outside newsfeed:

“As of October 21, 2024, a tentative agreement has been reached between the International Longshoremen’s Association (ILA) and the United States Maritime Alliance (USMX), which proposes a 62% salary increase for dock workers over six years. This development may temporarily alleviate tensions and decrease the immediate risk of strikes. However, significant issues remain unresolved, notably the contentious topic of automation and its implications for job security. These will be addressed in upcoming negotiations scheduled for January 15, 2025. While the current agreement offers a stopgap measure, it is uncertain whether it will lead to a long-term resolution, and there is potential for increased strike risks if the forthcoming discussions do not yield satisfactory outcomes. These reports, however, should be taken with caution as they might contain unverified information or biases.”

Querying Perplexity (AI predicts: 0.55 – confidence: 6)
Querying Claude (AI predicts: 0.35 – confidence: 5)
Querying Mistral (AI predicts: 0.4 – confidence: 6)
Querying Cohere (AI predicts: 0.3 – confidence: 6)
Querying OpenAI (AI predicts: 0.25 – confidence: 6)

Median from LLMs: 0.35
Base rate: 0.25 (from OpenAI)

SD: 0.1
Confidence: 6
Conf Mode: Normal
Mellers: 0.25
Reverse Mellers: 0.42
Theory of Mind: 0.5 (What did the LLMs think other LLMs predicted?)
Beta Distribution: 0.16
Close Type: A (B = cautious # closer to 50%; A/C = closer to extremes)
# LLM responses: 5
Model value (not submitted): 0.35

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

The recent tentative agreement between the International Longshoremen’s Association (ILA) and the United States Maritime Alliance (USMX) includes a significant 62% salary increase over six years for dock workers, which may temporarily reduce the risk of immediate strikes. However, critical issues remain unresolved, particularly the contentious topic of automation and its implications for job security, which are scheduled for negotiation on January 15, 2025. While the agreement suggests a willingness to negotiate, the short time frame before the end of Q1 2025 leaves limited room for resolving these tensions fully. Historically, unresolved issues like automation have led to strikes,indicating potential risks if future negotiations do not lead to satisfactory outcomes. External economic factors or political pressures might also affect the negotiation dynamics, making the situation unpredictable.

Runtime: 107 seconds.

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, 15%, up from yesterday’s 8%.

Obtaining outside newsfeed. Summarizing outside newsfeed:

“As of October 22, 2024, the potential merger between US Steel and Nippon Steel faces significant challenges and its likelihood of completion before January 21, 2025, appears low. The Biden administration has expressed concerns over national security, owing to which President Biden is anticipated to oppose Nippon Steel’s $14.9 billion bid for the American company. Further complicating matters, the United Steelworkers union is resisting the merger due to concerns about job security and a perceived lack of consultation, which could further stall the process. Meanwhile, Nippon Steel is actively lobbying, having spent $1.3 million in efforts to garner support for the merger. Additionally, the deal is under regulatory review in the US, adding to the uncertainty regarding its timeline and final outcome.”

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

Resolution of national security concerns by the Biden administration allowing the merger to proceed.

 Negotiations or agreements with the United Steelworkers union to address job security issues.

Completion of the regulatory review process without major objections.

Positive lobbying efforts by Nippon Steel leading to increased support for the merger.

Querying Perplexity (AI predicts: 0.2 – confidence: 6)
Querying Claude (AI predicts: 0.15 – confidence: 7)
Querying Mistral (AI predicts: 0.15 – confidence: 6)
Querying Cohere (AI predicts: 0.1 – confidence: 5)
Querying OpenAI (AI predicts: 0.15 – confidence: 4)

Median from LLMs: 0.15
Base rate: 0.1 (from OpenAI)

SD: 0.03
Confidence: 6
Conf Mode: Normal
Mellers: 0.04
Reverse Mellers: 0.3
Theory of Mind: 0.3 (What did the LLMs think other LLMs predicted?)
Beta Distribution: 0.07
Close Type: A (B = cautious # closer to 50%; A/C = closer to extremes)
# LLM responses: 5
Model value (not submitted): 0.15

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

The consensus among the AIs is that the US Steel/Nippon Steel merger is unlikely to be announced before January 21, 2025, mainly due to significant challenges such as national security concerns from the Biden administration, resistance from the United Steelworkers union over job security, and the ongoing US regulatory review, despite having received approvals elsewhere. While Nippon Steel’s substantial lobbying efforts, amounting to $1.3 million, could potentially influence the situation, the short timeframe and the complexity of these issues make timely resolution difficult. However, the prediction could be wrong if Nippon Steel successfully addresses these key concerns, the regulatory process progresses more favorably than expected, or if changes in the political landscape or union negotiations occur.

Runtime: 105 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 30%.

(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. 21, 2024
Oct. 17, 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