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, 46%
What is your question? 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 a strike in Q1 2025.
Do you have any other information you wish to pass along to assist in answering? (Hit Enter to skip)
ID: N/A
Obtaining outside newsfeed. Summarizing outside newsfeed:
“As of October 21, 2024, the situation involving dockworkers and a potential strike in the first quarter of 2025 remains uncertain. A tentative agreement, which includes a 62% salary increase over six years, has allowed workers to return temporarily, but key discussions concerning automation and job security are delayed until January 15, 2025. The dockworkers’ union, representing over 45,000 members, expresses ongoing concerns about the impact of automation on jobs. While the current agreement averts an immediate strike, if forthcoming negotiations do not address these concerns satisfactorily, the probability of a strike in Q1 2025 may increase. Due to these unresolved issues, the prospect of industrial action cannot be entirely ruled out.”
Querying Perplexity (AI predicts: 0.55 – confidence: 6)
Querying Claude (AI predicts: 0.4 – confidence: 6)
Querying Mistral (AI predicts: 0.6 – confidence: 7)
Querying Cohere(Error: Cohere is not returning an array)
Querying OpenAI (AI predicts: 0.3 – confidence: 5)
Median from LLMs: 0.48
Base rate: 0.3 (from OpenAI)
SD: 0.12
Confidence: 6
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: 0.07
Close Type: A (B = cautious # closer to 50%; A/C = closer to extremes)
# LLM responses: 4
Model value (not submitted): 0.46
We queried Perplexity, Claude, Mistral, OpenAI. A summary of what the responding AIs considered is as follows:
The AIs generally agree that while a recent agreement on a 62% salary increase over six years indicates progress and temporarily reduces the likelihood of an immediate strike, the delay in discussions on important issues like automation and job security until January 15, 2025, remains a significant concern. The union’s apprehensions regarding automation’s impact on jobs could escalate to a strike in Q1 2025 if not adequately addressed. Historical patterns of labor disputes in similar contexts add to this uncertainty. However, some AIs suggest that ongoing cooperation indicated by the recent salary agreement, along with potential economic or political interventions, might eventually lead to a resolution, reducing the likelihood of a strike. External influences or breakthroughs in negotiation strategies could also shift dynamics toward a more favorable outcome without industrial action.
Runtime: 131 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, 8%.
What is your question? What’s 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’s the probability of the US Steel/Nippon Steel merger being officially announced before January 21, 2025?
Obtaining outside newsfeed.
Summarizing outside newsfeed:
“Reports regarding the potential merger between US Steel and Nippon Steel suggest there is uncertainty about an official announcement occurring before January 2025 due to multiple factors. A key obstacle is the ongoing review by the Committee on Foreign Investment in the United States (CFIUS), which has been extended until December 2024, indicating that a decision may not be made until after the U.S. presidential election in November 2024. The merger also faces political opposition from stakeholders, including steelworkers and government officials, due to concerns about national security and impacts on the U.S. steel market. Additionally, market analysts have mixed opinions on the merger’s prospects, as the political climate and regulatory challenges present potential delays. Despite these hurdles, Nippon Steel remains committed to the acquisition.”
Querying Perplexity (AI predicts: 0.4 – confidence: 6)
Querying Claude (AI predicts: 0.35 – confidence: 5)
Querying Mistral (AI predicts: 0.15 – confidence: 6)
Querying Cohere (AI predicts: 0.2 – confidence: 4)
Querying OpenAI (AI predicts: 0.2 – confidence: 4)
Median from LLMs: 0.2
Base rate: 0.2 (from OpenAI)
SD: 0.1
Confidence: 5
Conf Mode: Low
Mellers: 0.08
Reverse Mellers: 0.33
Theory of Mind: 0.5 (What did the LLMs think other LLMs predicted?)
Beta Distribution: 0.45
Close Type: A (B = cautious # closer to 50%; A/C = closer to extremes)
# LLM responses: 5
Model value (not submitted): 0.08
We queried Perplexity, Claude, Mistral, Cohere, OpenAI. A summary of what the responding AIs considered is as follows:
The potential merger between US Steel and Nippon Steel is fraught with significant challenges, primarily due to the extended review by the Committee on Foreign Investment in the United States (CFIUS), which has been pushed to December 2024. This extension, coupled with political opposition from key stakeholders such as the United Steelworkers union and government officials like Pennsylvania Governor Josh Shapiro, underlines the national security and economic concerns surrounding the deal. The political climate, particularly with an upcoming U.S. presidential election in November 2024, further complicates the timeline, making an announcement by January 21, 2025, seem unlikely. Despite Nippon Steel’s commitment to the acquisition, the ensemble of regulatory hurdles and mixed opinions from market analysts contribute to extensive uncertainty about the merger’s prospects. However, early conclusion of the CFIUS review, easing of political pressures, or accelerated resolution of regulatory concerns could lead to a quicker announcement if the companies navigate these complexities effectively.
Runtime: 91 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 20%.
(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. 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).
