Updates from BestWorld’s AI Botmaster Jeremy Lichtman of Oct. 30, 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, 38%, up from yesterday’s 33%. 

Obtaining outside newsfeed. Summarizing outside newsfeed:

“As of October 30, 2024, the potential merger between US Steel and Nippon Steel remains uncertain, with various factors affecting the likelihood of an official announcement by January 21, 2025. The Committee on Foreign Investment in the United States (CFIUS) has extended its regulatory review of the merger, potentially delaying decisions until after the 2024 US presidential election. Investors are optimistic about the merger’s potential, as analysts note a possible 27% upside, but the ongoing political climate and regulatory hurdles make a 2024 closing unlikely. Despite Nippon Steel’s commitment to finalizing the deal by year-end, these challenges could postpone the timeline. Caution is advised when considering these reports, given possible rumors and lack of reliable information.”

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

– CFIUS completes its regulatory review of the merger and approves it without further delay. (Possible)

– The political climate remains stable enough post-2024 US presidential election to not interfere with the merger process. (Unlikely)

– Nippon Steel and US Steel agree to any additional terms or concessions required by regulatory bodies or stakeholders before January 21, 2025. (Possible)

– There are no significant rumors or misinformation that cause investor panic or legal challenges that could derail the merger. (Unlikely)

Querying Perplexity (AI predicts: 0.3 – confidence: 6)
Querying Claude (AI predicts: 0.35 – confidence: 5)
Querying Mistral (AI predicts: 0.25 – confidence: 6)
Querying OpenAI (AI predicts: 0.25 – confidence: 4)

Median from LLMs: 0.28
Base rate: 0.15 (from OpenAI)

SD: 0.04
Confidence: 5.5
Conf Mode: Low
Mellers: 0.15
Reverse Mellers: 0.38
Theory of Mind: 0.45 (What did the LLMs think other LLMs predicted?)
Beta Distribution: 0.001
Close Type: C (B = cautious # closer to 50%; A/C = closer to extremes)
# LLM responses: 4
Model value (not submitted): 0.38

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

The consensus among the various AIs is that the merger between US Steel and Nippon Steel faces significant challenges primarily due to an extended CFIUS review, political opposition from key figures like President Biden and Vice President Harris, and the uncertain political climate surrounding the 2024 US presidential election. These factors, coupled with the need for both companies to possibly agree on additional terms or concessions, create a scenario where a merger announcement by January 21, 2025, seems unlikely despite investor optimism. However, this prediction could prove incorrect if circumstances change; notably, if the CFIUS review concludes unexpectedly soon, the political environment stabilizes post-election, or if both companies efficiently resolve all regulatory and stakeholder concerns, the merger could indeed be announced earlier than anticipated.

Runtime: 59 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, 58%, up from yesterday’s 45%.

Obtaining outside  newsfeed.  Summarizing outside newsfeed:

“As of October 30, 2024, concerns regarding a potential strike by U.S. dockworkers in the first quarter of 2025 remain, despite a tentative agreement that temporarily suspends such actions until January 15, 2025. The International Longshoremen’s Association (ILA) and the U.S. Maritime Alliance (USMX) reached this short-term arrangement, which includes salary increases. However, unresolved issues, particularly related to automation and its impact on jobs, continue to be significant points of contention. Recent strike activities have had notable effects on U.S. ports, involving around 45,000 dockworkers, and historical context suggests that if negotiations do not address these concerns effectively, the likelihood of further labor disruptions may increase, potentially affecting various sectors and economic stability.”

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

– The ILA and the USMX fail to reach a long-term agreement by January 15, 2025. (Likely)

– Negotiations do not effectively address the contentious issues surrounding automation and job security. (Likely)

– Dockworkers vote in favor of a strike once the temporary suspension expires. (Possibly)

– No external interventions, such as government mediation or legislative action, occur to prevent a strike. (Unlikely)

Querying Perplexity (AI predicts: 0.65 – confidence: 7)
Querying Claude (AI predicts: 0.65 – confidence: 6)
Querying Mistral (AI predicts: 0.65 – confidence: 7)
Querying OpenAI (AI predicts: 0.5 – confidence: 5)

Median from LLMs: 0.65
Base rate: 0.3 (from OpenAI)

SD: 0.06
Confidence: 6.5
Conf Mode: Low
Mellers: 0.75
Reverse Mellers: 0.58
Theory of Mind: 0.5 (What did the LLMs think other LLMs predicted?)
Beta Distribution: 0.001
Close Type: B (B = cautious # closer to 50%; A/C = closer to extremes)
# LLM responses: 4
Model value (not submitted): 0.58

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 USMX, which includes salary increases, leaves significant issues such as automation and job security unresolved. This situation heightens the risk of labor disruptions if these core issues aren’t addressed by the January 15, 2025 deadline, as historical precedents show automation discussions are often contentious. Despite this, the potential for a strike is tempered by several factors: government intervention or legislative action could facilitate negotiations, and the temporary suspension of strikes might lead to a productive cooling-off period. Additionally, the goodwill generated from salary negotiations might encourage compromise, and external pressures for economic stability might spur more cooperative discussions between parties.

Runtime: 51 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. 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, 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