Updates from BestWorld’s AI Botmaster Jeremy Lichtman of Dec. 2, 2024

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

Welcome to the Multi-AI Oracle. Today, 8%, down from 40% Friday. 

Obtaining outside newsfeed. Summarizing outside newsfeed:

“The potential merger between U.S. Steel Corp. and Nippon Steel Corp. is currently facing considerable uncertainty and political tension. President Biden is expected to block the $14.9 billion merger on national security grounds, reflecting bipartisan concern over foreign control of a key American industry. Meanwhile, Nippon Steel is actively seeking to finalize the acquisition before any potential changes in U.S. political leadership, indicating the strategic importance it places on this deal. To address antitrust issues, Nippon Steel has proposed selling a significant stake in a joint venture. While there are arguments that the merger could benefit NATO allies by strengthening economic ties, the prevailing political climate appears unfavorable, casting doubt on whether the merger will be announced before January 21, 2025.”

Fact-checking news summary:
Here is a list of specific facts stated in the summary, along with their analysis:

1. **The potential merger between U.S. Steel Corp. and Nippon Steel Corp. is currently facing considerable uncertainty and political tension.**
– **Correctness**: Generally true based on the nature of international mergers involving significant industries, which often face scrutiny and uncertainty.
– **Relevance**: True. Uncertainty and political tension are directly related to the likelihood of the merger being announced.

2. **President Biden is expected to block the $14.9 billion merger on national security grounds.**
– **Correctness**: The correctness of this statement depends on insider or credible news sources and is speculative without verification. In analytical scenarios, such expectations can be true based on common governmental concerns, but specific actions need further evidence.
– **Relevance**: True. Presidential intervention on national security grounds would directly impact the merger announcement probability.

3. **Bipartisan concern exists over foreign control of a key American industry.**
– **Correctness**: True, as there is typically bipartisan concern in the U.S. about foreign control over critical industries and assets.
– **Relevance**: True. Bipartisan concern could influence legislative or executive action, affecting the likelihood of the merger.

4. **Nippon Steel is actively seeking to finalize the acquisition before any potential changes in U.S. political leadership.**
– **Correctness**: Potentially true if Nippon Steel perceives current political leadership as unfavorable to their plans.
– **Relevance**: True. Political leadership changes could alter the merger’s feasibility.
5. **Nippon Steel has proposed selling a significant stake in a joint venture to address antitrust issues.**
– **Correctness**: This requires more specific knowledge; it may be true as a common strategy to alleviate antitrust concerns in mergers.
– **Relevance**: True. Addressing antitrust issues is directly relevant to the likelihood of merger approval and announcement.

6. **There are arguments that the merger could benefit NATO allies by strengthening economic ties.**
– **Correctness**: Speculative and requires contextual geopolitical analysis. It might be a strategic opinion rather than a verifiable fact.
– **Relevance**: False. While international relations and benefits to NATO could play a role, they are less directly related to the specific announcement timeline.

7. **The prevailing political climate appears unfavorable, casting doubt on the merger being announced before January 21, 2025.**
– **Correctness**: True as an analytical conclusion given the details about political tensions and potential presidential intervention.
– **Relevance**: True. The political climate directly affects the timing of the merger announcement.

Each of these points helps assess the likelihood and timing of an official announcement concerning the merger.

Fact-checked summary: The potential merger between U.S. Steel Corp. and Nippon Steel Corp. is currently surrounded by considerable uncertainty and political tension, which are relevant factors in determining the likelihood of the merger being announced. A bipartisan concern exists in the United States over foreign control of critical American industries, directly influencing legislative or executive actions that could affect the merger’s progress. Additionally, the prevailing political climate, which is unfavorable due to these concerns, casts doubt on the merger being officially announced before January 21, 2025. These elements collectively suggest a low probability of the merger being finalized within the given timeframe.

OpenAI gives a base rate of 0.1. The following were considered in order to produce this base rate:

The base rate of 0.1 is based on the historical frequency of large international mergers facing significant political and regulatory challenges. These types of mergers often have a low success rate without clear political and economic alignment, especially when national industries are involved. The current political tension, combined with bipartisan concerns over foreign influence in critical American sectors, further decreases the likelihood of approval within the timeframe.

Some potential divergent considerations that might affect the base rate: Should there be a significant shift in political attitudes, either due to economic necessity or a change in political leadership that favors foreign investments, the likelihood of the merger could increase. Additionally, if U.S. Steel Corp. and Nippon Steel Corp. propose terms that assuage national security concerns or demonstrate substantial economic benefits that outweigh risks, this could influence the probability positively. However, given the current political climate, such changes are considered unlikely before January 21, 2025.

The following chain of events are necessary for the question to resolve positively: – Agreement must be reached between U.S. Steel Corp. and Nippon Steel Corp. to proceed with the merger. This is assessed as unlikely given the current political tension and uncertainty. – Approval from regulatory bodies in both the United States and Japan must be obtained. Given bipartisan concerns about foreign control, this is considered improbable. – Any necessary legislative actions or approvals must favor the merger. This is seen as highly improbable due to the prevailing political climate in the United States, which is unfavorable to foreign control of critical industries.

Querying Perplexity… (Error: Perplexity is not returning an array)
Querying Claude (AI predicts: 0.15 – confidence: 5)
Querying Mistral (AI predicts: 0.05 – confidence: 6)
Querying Cohere (AI predicts: 0.1 – confidence: 7)
Querying OpenAI (AI predicts: 0.05 – confidence: 3)

Median from LLMs: 0.08
Base rate: 0.1 (from OpenAI)
SD: 0.04
Confidence: 5.5
Conf Mode: Normal
Mellers: 0.03
Reverse Mellers: 0.16
Theory of Mind: 0.15 (What did the LLMs think other LLMs predicted?)
Beta Distribution: 0.7
Close Type: A (B = cautious # closer to 50%; A/C = closer to extremes)
# LLM responses: 4
Model value (not submitted): 0.08

We queried Claude, Mistral, Cohere, OpenAI (with news sourced from AskNews). A summary of what the responding AIs considered is as follows:

The reasoning across the different AI-generated lists suggests a low probability of the US Steel and Nippon Steel merger being officially announced before January 21, 2025, due to several significant obstacles. These include political tensions and uncertainties between the US and Japan, bipartisan fears over foreign control of critical American industries, and a historically low base rate for such large international mergers facing regulatory challenges. The merger requires prolonged regulatory approval from both US and Japanese bodies amid an unfavorable US political climate towards foreign acquisitions, further decreasing its likelihood within the short timeframe. However, counterarguments mention that an unexpected shift in political priorities or rapid economic changes could potentially fast-track the process, especially if the companies involved can formulate terms that address national security concerns and offer significant economic benefits. Still, such scenarios are considered improbable given the current circumstances.

Runtime: 135 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 a strike in Q1 2025.

Welcome to the Multi-AI Oracle. Today, 18%, down from 35% Friday.

Obtaining outside newsfeed.  Summarizing outside newsfeed:

“The recent tentative agreement between the International Longshore and Warehouse Union and the United States Maritime Alliance has brought a temporary end to the dockworkers’ strike, which lasted three days and involved 45,000 workers. This agreement includes a significant 62% wage increase over six years and extends the existing contract until January 15, 2025. However, despite this progress, concerns remain about future labor actions, as the union aims to negotiate further protections against potential job losses due to automation. As such, while this agreement signals a crucial step forward, the possibility of another strike in early 2025 cannot be dismissed, as outstanding issues continue to be negotiated.”

Fact-checking news summary: Here is a list of specific facts from the summary, along with analysis regarding their truthfulness and relevance to the outcome:

1. **Fact**: There was a tentative agreement between the International Longshore and Warehouse Union and the United States Maritime Alliance.
– **Check**: Internally consistent. Not enough external information provided to determine external truth.
– **Relevance**: True, as agreements influence the likelihood of future strikes.

2. **Fact**: The dockworkers’ strike lasted three days.
– **Check**: Internally consistent. Not enough external information to verify the duration of the strike.
– **Relevance**: True, the strike duration influences the context of labor disputes.

3. **Fact**: The strike involved 45,000 workers.
– **Check**: Internally consistent. Not enough external information to verify the number of workers involved.
– **Relevance**: True, as the number of workers involved impacts the negotiations and potential future strikes.

4. **Fact**: The agreement includes a 62% wage increase over six years.
– **Check**: Internally consistent; however, a 62% increase over six years seems unusually high and may not be typical in such negotiations. External validation needed.
– **Relevance**: True, as wage increases directly affect worker satisfaction and likelihood of future strikes.

5. **Fact**: The agreement extends the existing contract until January 15, 2025.
– **Check**: Internally consistent. Not enough external information.
– **Relevance**: True, as the contract term is relevant to timing of future negotiations and potential strikes.

6. **Fact**: The union aims to negotiate protections against job losses due to automation.
– **Check**: Internally consistent and plausible given industry trends.
– **Relevance**: True, as automation and job protections are central issues in labor negotiations that could lead to strikes.

7. **Fact**: The possibility of another strike in early 2025 cannot be dismissed.
– **Check**: Internally consistent; reflects logical reasoning based on ongoing negotiations and unresolved issues.
– **Relevance**: True, directly addressing the question about the probability of a strike in Q1 2025.

Overall, while the internal consistency of the facts is maintained, some facts require external validation to confirm their accuracy. All the identified facts are relevant to the potential outcome concerning the likelihood of a strike in early 2025.

Fact-checked summary: There is a tentative agreement between the International Longshore and Warehouse Union and the United States Maritime Alliance, which is relevant as such agreements generally influence the likelihood of future strikes. The dockworkers’ recent strike lasted three days and involved 45,000 workers, with both factors affecting the context of labor disputes and negotiations. The agreement includes extending the existing contract until January 15, 2025, and incorporates a 62% wage increase over six years, directly impacting worker satisfaction and future strike probabilities. The union aims to negotiate protections against job losses due to automation, a central issue that could lead to labor disputes. Given ongoing negotiations and unresolved issues, the possibility of another strike in early 2025 cannot be dismissed, as it is directly relevant to understanding the probability of a strike in Q1 2025.

OpenAI gives a base rate of 0.2. The following were considered in order to produce this base rate:

The base rate is calculated by assessing the historical frequency of dockworker strikes following major agreements, as well as the specifics of the current situation. Historically, strike occurrences right after a significant wage increase and contract extension are low, especially when labor issues such as automation are being actively negotiated. The recent tentative agreement and extension suggest an environment of cooperation and possibility for resolution. While labor negotiations carry uncertainty, the presence of an active contract until early 2025 reduces the likelihood of a strike during Q1 2025.

Some potential divergent considerations that might affect the base rate: Factors that might increase the likelihood include a significant breakdown in negotiations over automation protections or other unexpected labor disputes arising. If either party fails to adhere to the agreement terms, this could lead to increased tensions and potential for strikes. However, if automation concerns are amicably resolved and the agreement is honored, the probability of a strike will likely remain low.

The following chain of events are necessary for the question to resolve positively: – Failure to reach agreement on automation protections during ongoing negotiations (unlikely).
– Dissatisfaction among union members despite the 62% wage increase (unlikely).
– Escalation of tensions between the union and the United States Maritime Alliance before January 15, 2025 (unlikely).

Querying Perplexity… (Error: Perplexity is not returning an array)
Querying Claude (AI predicts: 0.15 – confidence: 6)
Querying Mistral (AI predicts: 0.15 – confidence: 6)
Querying Cohere (AI predicts: 0.2 – confidence: 7)
Querying OpenAI (AI predicts: 0.2 – confidence: 6)

Median from LLMs: 0.18
Base rate: 0.2 (from OpenAI)
SD: 0.03
Confidence: 6
Conf Mode: Normal
Mellers: 0.1
Reverse Mellers: 0.27
Theory of Mind: 0.275 (What did the LLMs think other LLMs predicted?)
Beta Distribution: 0.84
Close Type: A (B = cautious # closer to 50%; A/C = closer to extremes)
# LLM responses: 4
Model value (not submitted): 0.18

We queried Claude, Mistral, Cohere, OpenAI (with news sourced from AskNews). A summary of what the responding AIs considered is as follows:

The consensus among the AIs is that the probability of a strike in Q1 2025 is low, mainly due to factors such as the recent substantial wage increase of 62%, the contract extension until January 2025, and the active negotiations regarding automation protections. Historically, strikes are infrequent after major wage agreements, indicating a collaborative environment that lowers the risk of immediate strike action. Despite the positive indicators, the possibility of a strike cannot be entirely dismissed due to ongoing concerns about automation and potential conflicts arising before January 15. External economic factors and unresolved labor disputes could escalate tensions, challenging the current consensus of low strike probability.

Runtime: 132 seconds.



Our bots vs humans experiments

Our concluded FED rate increase competition.

All our current bot projects

Guide to our Multi-AI Oracle’s Reports 

Median: 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