Updates from BestWorld’s AI Botmaster Jeremy Lichtman of Jan. 28, 2025

The International Longshoremen’s Association returned 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, 15%, same as yesterday. Obtaining outside newsfeed. News from various sources. Based on the provided news articles, here’s a summary of the US port workers strike situation in early 2025:

In early January 2025, a major potential strike was averted when the labor union representing approximately 45,000 U.S. dockworkers reached a tentative agreement with port employers at East and Gulf Coast ports. The key issue in the negotiations was the implementation of automation technology at ports, with the union securing certain limits on technology adoption to protect jobs. The deal was reached just days before a January 15 strike deadline that could have significantly impacted the U.S. economy.

The agreement appears to represent a compromise between the union’s concerns about job preservation and employers’ desires to modernize port operations. The deal followed months of negotiations and came after a previous work stoppage in October 2024. While specific details of the agreement weren’t fully disclosed in the articles, it seems to include provisions for some level of automation while providing job protections for union members.
Most recent developments show that this agreement has helped maintain stability at major U.S. ports, avoiding what could have been a significant disruption to supply chains and the broader economy. The resolution of this dispute is particularly significant given the essential role that dockworkers play in maintaining the flow of international trade through U.S. ports.

Summarizing outside newsfeed:
“In January 2025, a potential strike by U.S. dockworkers was averted when their union reached a tentative agreement with port employers at East and Gulf Coast ports, just before a critical January 15 deadline. The negotiations primarily centered around the adoption of automation technology at ports, with the union securing certain limitations on its implementation to protect jobs. This agreement, which follows months of discussions and a previous work stoppage in October 2024, appears to strike a balance between the union’s job security concerns and employers’ modernization goals, though details remain partially undisclosed. The resolution has provided stability, helping to prevent major disruptions to the U.S. economy by ensuring continued operations at these crucial ports.”

Fact-checking news summary:
Here’s a list of specific facts from the summary, along with assessments of their accuracy, importance to resolving the question, and relevance to the outcome:

1. **Fact:** In January 2025, a potential strike by U.S. dockworkers was averted when their union reached a tentative agreement with port employers at East and Gulf Coast ports, just before a critical January 15 deadline.
– **Correctness:** True, according to the summary’s internal logic. The timeline given implies the success of last-minute negotiations.
– **Importance:** Critical – It directly addresses the likelihood of a strike and indicates it was avoided.
– **Relevance:** True – Preventing a strike is relevant to determining the probability of a strike in Q1 2025.

2. **Fact:** The negotiations primarily centered around the adoption of automation technology at ports.
– **Correctness:** True, according to the summary’s internal logic.
– **Importance:** Important – Since automation was a primary negotiation topic, understanding its resolution affects union satisfaction and strike probability.
– **Relevance:** True – It affects the union’s bargaining position and potential for future disputes.

3. **Fact:** The union secured certain limitations on automation’s implementation to protect jobs.
– **Correctness:** True, according to the summary’s internal logic.
– **Importance:** Important – Union job protection measures affect the overall resolution and satisfaction with the agreement.
– **Relevance:** True – These limitations are relevant to union acceptance and hence the probability of a strike.

4. **Fact:** The agreement follows months of discussions and a previous work stoppage in October 2024.
– **Correctness:** Internally consistent (work stoppage in October 2024 aligns with a lengthy negotiation process). External verification would need additional data sources.
– **Importance:** Important – Historical context of negotiations and previous disruptions are crucial for predicting future strike risks.
– **Relevance:** True – Past work stoppages provide context that can influence future actions.

5. **Fact:** The agreement appears to strike a balance between the union’s job security concerns and employers’ modernization goals, though details remain partially undisclosed.
– **Correctness:** True, according to the summary’s internal logic.
– **Importance:** Important – Balance suggests lasting resolution, impacting future strike probability.
– **Relevance:** True – It is relevant since perceived fairness affects ongoing union-employer relations.

6. **Fact:** The resolution has provided stability, helping to prevent major disruptions to the U.S. economy by ensuring continued operations at crucial ports.
– **Correctness:** True, according to the summary’s internal logic.
– **Importance:** Important – Stability of operations impacts economic predictions and labor relations.
– **Relevance:** True – Relevant given the focus on avoiding a strike and economic impact.

Overall, the specific facts provide a basis for assessing the probability of a strike, with many details pointing towards reduced strike likelihood by resolving major issues and fostering temporary stability.

Fact-checked summary:
In January 2025, a potential strike by U.S. dockworkers was averted when their union reached a tentative agreement with port employers at East and Gulf Coast ports just before a critical January 15 deadline, which is crucial as it directly addresses the likelihood of a strike and indicates it was avoided. The negotiations primarily centered around the adoption of automation technology at ports, and the union successfully secured certain limitations on automation’s implementation to protect jobs. This is important as it affects the union’s satisfaction with the agreement. The agreement followed months of discussions and a previous work stoppage in October 2024, highlighting the historical context of negotiations influencing future strike risks. The resolution appears to strike a balance between the union’s job security concerns and employers’ modernization goals, suggesting a lasting resolution that impacts future strike probability. Moreover, it has provided stability by ensuring continued operations at crucial ports, which is significant for avoiding major disruptions to the U.S. economy. Collectively, these details suggest a reduced likelihood of a strike in Q1 2025 by addressing major issues and fostering temporary stability.

OpenAI gives a base rate of 0.1. The following were considered in order to produce this base rate:
The base rate for the likelihood of a strike in Q1 2025 considers the successful recent resolution of the negotiation between dockworkers and port employers, which directly addressed the main issue of automation. Historically, strikes after such agreements are less common due to the temporary stability provided and satisfaction of key union demands, suggesting a base rate of 0.1 or 10% chance for a strike. This is consistent with historical events where similar negotiations led to a period of industrial peace until the next contract issue arose.

Some potential divergent considerations that might effect the base rate:
Factors that could lead to a different outcome than the base rate include union member dissatisfaction and multiple rejections of the agreement, leading to renewed negotiations or a strike. Additionally, if employers push for quicker automation implementation, it could potentially reignite tensions. Changes in economic conditions, such as a sudden downturn affecting shipping volumes or port operations, could amplify pressures on both sides, increasing strike likelihood beyond the 10% base rate.

The following chain of events are necessary for the question to resolve positively:
-The tentative agreement between U.S. dockworkers and port employers fails to be ratified by union members. unlikely
– New, significant disagreements or disputes arise regarding automation technology after the January agreement. unlikely
– Substantial economic or political changes increase pressure on dockworkers or employers, leading to a strike. unlikely

Querying Claude (AI predicts: 0.15 – confidence: 7)
Querying Mistral (AI predicts: 0.15 – confidence: 6)
Querying OpenAI (AI predicts: 0.15 – confidence: 6)
Question Type: Binary
Median from LLMs: 0.15
Base rate: 0.1 (from OpenAI)
SD: 0
Confidence: 6
Conf Mode: Normal
Mellers: 0.07
Reverse Mellers: 0.24
Theory of Mind: 0.25 (What did the LLMs think other LLMs predicted?)
Beta Distribution: 0.001
Close Type: A (B = cautious # closer to 50%; A/C = closer to extremes)
# LLM responses: 3

Model value: 0.15

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

The recent resolution of salary disputes and a tentative agreement on January 15, 2025, have significantly reduced the likelihood of a strike by U.S. dockworkers in Q1 2025. Historical data supports a low probability of strikes immediately following successful negotiations, primarily due to temporary stability and satisfaction of union demands, including those related to automation and job security. While the base strike probability is estimated around 10%, potential risks such as union dissatisfaction, rapid changes in automation policy, unforeseen economic pressures, or rejection of the agreement during ratification could moderately increase strike likelihood. Nevertheless, the short timeframe in combination with the recent agreement provides an overall environment that maintains a lower likelihood for a strike, unless significant disruptive events occur.





How many seats will the Conservative Party win in Canada’s next federal parliamentary election?

Welcome to the Multi-AI Oracle. Today:  How many seats will the Conservative Party win in Canada’s next federal parliamentary election?
* less than 172: 15%
* between 172 and 205: 45%
* between 206 and 240: 30%
* more than 240: 10%

Most recent news (from the past 24-48 hours):
Prime Minister Justin Trudeau is planning to fill 10 current Senate vacancies before stepping down as Liberal Party leader. According to recent reports, the selection process is already underway and won’t be affected by the prorogation of Parliament. This move would allow Trudeau to make his final mark on the Senate’s composition before his successor is chosen. The Senate appointments are part of Trudeau’s established independent advisory process for selecting senators, which he implemented to make the upper chamber less partisan.

Regarding Canadian markets and the upcoming political transition:
Equity investors are showing optimism about Canada’s looming election, hoping for increased returns under potential new leadership. After nine years of Liberal Party governance, markets are anticipating a possible shift in economic priorities. The prospect of a change in government has generated positive sentiment among investors looking for new economic directions and policies.
The Conservative Party, led by Pierre Poilievre, continues to maintain an active presence with public events and political messaging. Recent activities include organizing rallies and releasing statements, including a recent commemoration of Lincoln Alexander Day, as they position themselves for a potential upcoming federal election.

This news collectively suggests Canada is in a period of political transition, with implications for governance, economic policy, and market sentiment.

Summarizing outside newsfeed:
“Recent developments in Canada suggest a period of political transition, with Prime Minister Justin Trudeau reportedly planning to fill 10 Senate vacancies before stepping down as leader of the Liberal Party. This move would enable him to influence the Senate’s composition through his independent advisory process, which aims to reduce partisanship. Meanwhile, equity investors are expressing optimism about the prospect of new economic policies under potential new leadership, as the country looks toward a possible change after nine years of Liberal governance. The Conservative Party, led by Pierre Poilievre, is maintaining an active presence with public events and messaging, indicating their readiness for an upcoming federal election. As these events unfold, they carry potential implications for Canada’s governance, economic strategies, and market sentiment.”

Fact-checking news summary:
Here is a list of specific facts from the summary, along with an analysis of their correctness, importance to the question, and relevance to the outcome.

1. **Fact: Prime Minister Justin Trudeau is reportedly planning to fill 10 Senate vacancies before stepping down as leader of the Liberal Party.**
– Correctness: True. Public reports indicate Trudeau has expressed intentions to fill Senate vacancies.
– Importance to the question: Lesser importance. This fact is more about the future influence on the Senate rather than an immediate impact on the number of seats the Conservative Party might win.
– Relevance to the outcome: False. This does not have a direct impact on the number of seats the Conservative Party will win.

2. **Fact: Trudeau’s move would enable him to influence the Senate’s composition through his independent advisory process, aiming to reduce partisanship.**
– Correctness: True. The independent advisory process aims to appoint non-partisan senators.
– Importance to the question: Unimportant. This is related to the Senate, which is separate from elections for the House of Commons.
– Relevance to the outcome: False. It is unrelated to the Conservatives’ seat count in the federal parliamentary election.

3. **Fact: Equity investors are expressing optimism about the prospect of new economic policies under potential new leadership.**
– Correctness: True. Market sentiment can suggest optimism towards new leadership and economic policies.
– Importance to the question: Lesser importance. While this indicates a potential positive view on leadership change, it does not directly relate to seat numbers.
– Relevance to the outcome: False. Economic policies affect broader markets, not directly the seat count for the Conservative Party.

4. **Fact: Canada is looking toward a possible change after nine years of Liberal governance.**
– Correctness: True. The Liberal Party, led by Trudeau, has been in power since 2015.
– Importance to the question: Important. A long period of governance may influence public opinion and affect voting patterns.
– Relevance to the outcome: True. It could influence the number of seats the Conservative Party might win if voters are seeking change.

5. **Fact: The Conservative Party, led by Pierre Poilievre, is maintaining an active presence with public events and messaging.**
– Correctness: True. Poilievre and the Conservative Party have been engaging actively with the public.
– Importance to the question: Important. The Conservative Party’s campaign activities and public engagement are directly related to their potential success in the election.
– Relevance to the outcome: True. Measures like active campaigning may contribute to their success in the election.

6. **Fact: These events carry potential implications for Canada’s governance, economic strategies, and market sentiment.**
– Correctness: True. Political changes can have widespread implications on governance and economics.
– Importance to the question: Lesser importance. While broadly relevant, this does not directly quantify or specify seat counts for the Conservative Party.
– Relevance to the outcome: False. Broader implications do not directly indicate the number of seats the Conservative Party will secure.

Fact-checked summary:
The Conservative Party, led by Pierre Poilievre, maintains an active presence with public events and messaging, which is important to their potential success in the next federal parliamentary election in Canada. This active campaigning could influence their election outcomes by engaging voters and increasing support. Additionally, after nine years of Liberal governance under Prime Minister Justin Trudeau, Canada may be looking toward a change, which could influence public opinion and voting patterns. This context is relevant as it may impact the number of seats the Conservative Party might win, as voters may seek an alternative to the long-standing Liberal leadership.

Querying Claude (AI predicts: [“less than 172”: 0.25, “between 172 and 205”: 0.45, “between 206 and 240”: 0.25, “more than 240”: 0.05] – confidence: 4)
Querying Mistral (AI predicts: [“less than 172”: 0.1, “between 172 and 205”: 0.3, “between 206 and 240”: 0.4, “more than 240”: 0.2] – confidence: 6)
Querying OpenAI (AI predicts: [“less than 172”: 0.15, “between 172 and 205”: 0.45, “between 206 and 240”: 0.3, “more than 240”: 0.1] – confidence: 7)
Question Type: Multiple Choice
Confidence: 6
# LLM responses: 3

Model value:
* less than 172: 0.15
* between 172 and 205: 0.45
* between 206 and 240: 0.3
* more than 240: 0.1

We queried Claude, Mistral, OpenAI. A summary of what the responding AIs considered is as follows:
The various AI predictions suggest that the Canadian Conservative Party, led by Pierre Poilievre, might increase their seat count due to several factors: active campaigning, voter fatigue with the long-standing Liberal government under Justin Trudeau, and historical trends of incumbent parties losing support over time. Current polling supports a potential shift towards the Conservatives, though achieving a large majority remains challenging due to historical precedents and the number of seats in Parliament. However, these predictions face uncertainties as public opinion polls can be unreliable, and unforeseen events—political scandals, economic changes, or shifts in voter sentiment towards other parties—could significantly impact election outcomes. The Liberal Party may also counter with effective strategies, maintaining or regaining support, adding further unpredictability to the forecasts.

Runtime: 147 seconds for both questions combined on this page.

Past Multi-AI Oracle Forecasts

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