Updates from BestWorld’s AI Botmaster Jeremy Lichtman of Nov. 11, 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, 18%, down from Friday’s 32%. 

Obtaining outside newsfeed. Summarizing outside newsfeed:

”The potential merger between US Steel and Nippon Steel, valued at $14.9 billion, is facing significant uncertainty due to regulatory and political challenges. The U.S. Committee on Foreign Investment is scrutinizing the deal over concerns about foreign ownership and the impact on U.S. jobs. Both President Biden and former President Trump have expressed opposition, emphasizing the preference for US Steel to remain under American ownership. Nippon Steel has announced a delay in the acquisition process, meaning any official decision is unlikely before the November elections and possibly extending into early 2025. Political dynamics and the upcoming recommendations from the Committee on Foreign Investment will be crucial in determining the merger’s future.”

Fact-checking news summary:

Here is a list of specific facts stated in the summary, along with an assessment of their correctness and relevance to the outcome:

1. **Fact:** The merger between US Steel and Nippon Steel is valued at $14.9 billion.
– Correctness: True/False (Requires external data to verify the exact valuation of this potential merger.)
– Relevance: True (The valuation is relevant as it impacts financial and strategic considerations for the merger.)

2. **Fact:** The merger is facing significant uncertainty due to regulatory and political challenges.
– Correctness: True (Regulatory and political challenges are common concerns in large, multinational mergers.)
– Relevance: True (These challenges directly affect the likelihood of the merger being announced.)

3. **Fact:** The U.S. Committee on Foreign Investment is scrutinizing the deal over concerns about foreign ownership and the impact on U.S. jobs.
– Correctness: True/False (Requires external data to confirm the Committee’s involvement and specific concerns.)
– Relevance: True (The Committee’s decision influences the timing and approval of the merger.)

4. **Fact:** Both President Biden and former President Trump have expressed opposition to the merger.
– Correctness: True/False (Verification needed on whether both have publicly opposed the merger.)
– Relevance: True (Presidential opposition impacts political and public sentiment, influencing the merger process.)

5. **Fact:** There is a preference for US Steel to remain under American ownership.
– Correctness: True (This aligns with typical political and public stances regarding foreign acquisitions of key domestic industries.)
– Relevance: True (This preference directly influences political decisions and regulatory scrutiny.)

6. **Fact:** Nippon Steel has announced a delay in the acquisition process.
– Correctness: True/False (Needs confirmation if Nippon Steel has officially announced a delay.)
– Relevance: True (A delay impacts the timeline of the merger announcement.)

7. **Fact:** An official decision is unlikely before the November elections and may extend into early 2025.
– Correctness: True/False (Depends on the accuracy of the internal strategic assessments and public announcements regarding the timeline.)
– Relevance: True (This directly pertains to the likelihood of the merger being announced before January 21, 2025.)

8. **Fact:** Political dynamics and upcoming recommendations from the Committee on Foreign Investment will be crucial in determining the merger’s future.
– Correctness: True (Political dynamics and recommendations from such a Committee are typically influential in merger approvals.)
– Relevance: True (These factors are pivotal in affecting whether the merger proceeds and is announced.)

In summary, while some assertions require external verification for accuracy, all stated facts are relevant to forecasting the likelihood of the merger being announced before the specified date.

Fact-checked summary:

The potential merger between US Steel and Nippon Steel faces significant uncertainty due to common regulatory and political challenges associated with large, multinational mergers. There is a preference in political and public circles for US Steel to remain under American ownership, which directly influences political decisions and regulatory scrutiny. Political dynamics and upcoming recommendations from the U.S. Committee on Foreign Investment, a key body scrutinizing such deals, will be crucial in determining the merger’s future. These factors collectively impact the likelihood of the merger being officially announced before January 21, 2025.

OpenAI gives a base rate of 0.15
The following were considered in order to produce this base rate:

The base rate for this merger being announced is low due to several key factors. Historically, multinational mergers involving American companies and foreign entities face intense scrutiny, especially in sectors deemed strategic or sensitive, reducing the likelihood of a favorable outcome. Regulatory obstacles are significant, with the U.S. Committee on Foreign Investment known for caution in cases where foreign ownership might be perceived as conflicting with national interests. Added to this is the current political climate that prioritizes American ownership of certain industries. Past cases have shown similar mergers failing or being delayed significantly due to such challenges. Using the 7 Stories framework, historical precedents, political dynamics, and the power of regulatory bodies significantly influence the calculated base rate.

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

– Regulatory approval is obtained from relevant authorities, particularly the U.S. Committee on Foreign Investment which is likely (probable) to be difficult given political preferences.
– US Steel and Nippon Steel reach a mutual agreement on merger terms which is likely (probable) but must consider complex negotiations given the multinational nature.
– Political opposition is sufficiently addressed or mitigated, which is unlikely (improbable) due to strong preferences for US Steel to remain American-owned.
– Public sentiment is effectively managed to prevent it from influencing regulatory and political decision-making processes, which is possible (plausible).

Querying Perplexity (AI predicts: 0.2 – confidence: 6)
Querying Claude (AI predicts: 0.15 – confidence: 5)
Querying Mistral (AI predicts: 0.25 – confidence: 6)
Querying OpenAI (AI predicts: 0.1 – confidence: 6)

Median from LLMs: 0.18
Base rate: 0.15 (from OpenAI)

SD: 0.06
Confidence: 6
Conf Mode: Normal
Mellers: 0.1
Reverse Mellers: 0.27
Theory of Mind: 0.3 (What did the LLMs think other LLMs predicted?)
Beta Distribution: 0.3
Close Type: A (B = cautious # closer to 50%; A/C = closer to
extremes)
# LLM responses: 4
Model value (not submitted): 0.18

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

The predictions regarding the US Steel and Nippon Steel merger highlight several potential hurdles and considerations. Key challenges include regulatory obstacles, particularly scrutiny from the U.S. Committee on Foreign Investment, due to a political climate that favors American ownership in strategic sectors, such as steel production. Historical precedents of multinational mergers involving American companies face similar hurdles, adding to the complexity of negotiations and approvals. However, some room for optimism exists if political dynamics shift, regulatory bodies expedite processes, or if Nippon Steel manages to effectively address political and public concerns. Additionally, unexpected changes such as economic pressures or favorable deal structures might enhance the merger’s chances of being announced by January 2025.

Runtime: 84 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, 57%, up from Friday’s 40%.

Obtaining outside newsfeed.  Summarizing outside newsfeed:

“Recent reports indicate that negotiations are ongoing concerning U.S. dockworkers who have temporarily suspended their strike until January 15, 2025, as discussions on a new six-year contract continue. The critical issues under negotiation include wages, with some unverified demands suggesting significant salary increases of up to 77% over seven years, and the contentious topic of automation, which is seen by the union as a threat to jobs. If a resolution is not reached, there is a possibility of a strike in early 2025, potentially impacting supply chains and the economy. However, details of the negotiations are still unfolding, and the situation is subject to change.”

Fact-checking news summary:

To address the question, I’ll list specific facts from the summary, check their correctness for external and internal consistency, and assess their relevance to the probability of a strike in Q1 2025.

1. **Fact: Negotiations are ongoing concerning U.S. dockworkers.**
– **Correctness: True (External/Internal Consistency)**
– This is consistent with reports on ongoing labor negotiations.
– **Relevance to Outcome: True**
– The ongoing negotiations are directly related to the potential for a strike.

2. **Fact: U.S. dockworkers have temporarily suspended their strike until January 15, 2025.**
– **Correctness: True (External/Internal Consistency)**
– This aligns with the original question suggesting discussions are set for January 15, 2025.
– **Relevance to Outcome: True**
– Suspension of the strike is a key factor in assessing the likelihood of a strike in Q1 2025.

3. **Fact: Discussions on a new six-year contract continue.**
– **Correctness: True (External/Internal Consistency)**
– Continuing contract discussions are commonly part of such negotiations.
– **Relevance to Outcome: True**
– The contract duration is relevant as it influences negotiation dynamics and potential strike outcomes.

4. **Fact: Critical issues under negotiation include wages.**
– **Correctness: True (External/Internal Consistency)**
– Wage negotiations are a standard part of labor discussions.
– **Relevance to Outcome: True**
– Wage agreements are crucial to employee satisfaction and potential strike avoidance.

5. **Fact: Some unverified demands suggest significant salary increases of up to 77% over seven years.**
– **Correctness: False (External/Internal Consistency)**
– The percentage and timeframe of the salary increase demand do not match typical ranges and seem exaggerated without verification.
– **Relevance to Outcome: True**
– The scale of wage demands can impact the probability of strike prolongation or resolution.

6. **Fact: Automation is a contentious topic seen by the union as a threat to jobs.**
– **Correctness: True (External/Internal Consistency)**
– Automation concerns are frequently cited in labor negotiations.
– **Relevance to Outcome: True**
– Automation issues could influence decision-making on strikes due to job security concerns.

7. **Fact: If a resolution is not reached, there’s a possibility of a strike in early 2025.**
– **Correctness: True (External/Internal Consistency)**
– This is a standard assumption during unresolved labor negotiations.
– **Relevance to Outcome: True**
– This directly impacts the probability of a strike in Q1 2025.
8. **Fact: Potential impacts include disruptions to supply chains and the economy.**
– **Correctness: True (External/Internal Consistency)**
– Labor strikes in critical sectors like ports typically affect supply chains and the economy.
– **Relevance to Outcome: False**
– While impactful, this fact doesn’t directly influence the probability of a strike occurring; it describes consequences.

By analyzing these facts, we gain insights into the dynamics at play and can better assess the probability of a strike based on ongoing negotiation developments and sticking points.

Fact-checked summary:

Negotiations are ongoing regarding U.S. dockworkers, with critical issues under discussion including wages and automation. These negotiations are directly relevant to the potential for a strike in Q1 2025. Currently, U.S. dockworkers have temporarily suspended their strike until January 15, 2025, which aligns with the planned return to the bargaining table on that date to discuss these issues. The discussions also include talks of a new six-year contract, with wage agreements being a standard part of such labor negotiations. As automation is a contentious topic, viewed by the union as a threat to job security, it remains a significant negotiation point. If a
resolution is not reached, there is an acknowledged possibility of a strike in early 2025, influencing the likelihood of a strike occurring in Q1 2025.

OpenAI gives a base rate of 0.4

The following were considered in order to produce this base rate:

In assessing the likelihood of a dockworkers’ strike in Q1 2025, we’ve considered past instances of labor negotiations on the West Coast. Historically, negotiations have often been fraught, especially on contentious issues like automation, which tends to exacerbate union concerns over job security. The fact that there has already been a temporary suspension of strikes shows willingness to negotiate, yet the alignment of negotiations at the start of Q1 2025 with no contract in place increases strike risk. Assuming historical resolution rates are similar despite current contentious issues, the base rate of strikes occurring in similar high-tension scenarios is approximately 40%. This accounts for both successful and failed negotiations in the past while recognizing that wage and automation discussions will likely be pivotal negotiation points.

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

– Negotiations fail to reach a satisfactory agreement on wages by January 15, 2025 (50% probability).
– The union’s concerns over automation are not adequately addressed in the negotiations (60% probability).
– No alternative dispute resolution mechanisms successfully avert a strike (40% probability).

Querying Perplexity (AI predicts: 0.55 – confidence: 7)
Querying Claude (AI predicts: 0.65 – confidence: 6)
Querying Mistral (AI predicts: 0.65 – confidence: 7)
Querying OpenAI (AI predicts: 0.45 – confidence: 6)

Median from LLMs: 0.6
Base rate: 0.4 (from OpenAI)

SD: 0.08
Confidence: 6.5
Conf Mode: Low
Mellers: 0.64
Reverse Mellers: 0.57
Theory of Mind: 0.5 (What did the LLMs think other LLMs predicted?)
Beta Distribution: 0.01
Close Type: B (B = cautious # closer to 50%; A/C = closer to extremes)
# LLM responses: 4
Model value (not submitted): 0.57

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

The likelihood of a dockworkers’ strike in Q1 2025 hinges on ongoing negotiations between the dockworkers’ union and port authorities, focusing primarily on automation and wage issues. Historically, automation has been a significant trigger for strikes due to job security concerns, and the historical strike rate in similar scenarios is roughly 40%. The temporary suspension of strikes until January 15, 2025, suggests a willingness to negotiate but also leaves room for tension if no resolution is reached. While salary agreements have been achieved, the unresolved issue of automation and no existing contract raise the strike probability. However, factors such as successful wage agreements, potential government intervention, alternative dispute resolution mechanisms, or significant concessions from the port regarding automation could prevent a strike. Ultimately, the risk
remains elevated but negotiable outcomes before mid-January could mitigate the likelihood of industrial action.

Runtime: 73 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%. Michael’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:

Nov. 8, 2024
Nov. 7, 2024
Nov. 6, 2024
Nov. 5, 2024
Nov. 4, 2024
Nov. 1, 2024
Oct. 31, 2024
Oct. 30, 2024
Oct. 29, 2024
Oct. 28, 2024
Oct. 25, 2024
Oct. 24, 2024
Oct. 23, 2024
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, 2024

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