Updates from BestWorld’s AI Botmaster Jeremy Lichtman of Feb. 26, 2025

Given the agreement of the US dockworkers union (International Longshoremen’s Association) to salary increases, both union and the port 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, it is 8%, down from yesterday’s 20%, further down from Monday’s 40%. [Jeremy’s note: The ILA ratified, and that made it into the news, so the bot finally understands the question properly.]

 Obtaining outside newsfeed. News from various sources. Based on the most recent news articles, here’s a summary of the US dockworkers situation:

Most recently (February 2024), the dockworker union that caused significant disruption to US container trade last October has successfully ratified a new six-year labor contract at Eastern US ports. This represents a major development in stabilizing port operations along the East Coast.

In Alberta, Canada, there is ongoing tension as thousands of school support workers are currently on strike, with union organizers claiming that provincial government mandates are interfering with collective bargaining processes. Similarly, in Toronto, around 30,000 city workers represented by CUPE Local 79 are moving closer to a potential strike after filing a “no board” request, affecting various sectors including public health, city operations, and social services.

Looking back to earlier events, negotiations between the U.S. Maritime Alliance and the International Longshoreman’s Association had resumed in January to prevent a dock worker strike. Additionally, in British Columbia, the BC General Employees’ Union (BCGEU) is entering negotiations for contracts covering approximately 34,000 provincial workers, suggesting continued activity in public sector labor negotiations across North America.

The most significant recent development is the successful ratification of the East Coast dockworkers’ contract, which should provide stability to US port operations for the next six years.

Summarizing outside newsfeed:

“The recent newsfeed highlights various ongoing labor negotiations and strikes, with a cautious focus on their potential impacts. A major development is the ratification of a new six-year contract by the East Coast dockworkers’ union, which is expected to stabilize port operations in the U.S. Meanwhile, tensions continue in Canada, with school support workers on strike in Alberta and Toronto city workers nearing a strike, partly due to alleged government interference in bargaining processes. Additionally, labor discussions are active with the BC General Employees’ Union in British Columbia and resumed talks between the U.S. Maritime Alliance and the International Longshoreman’s Association. These events suggest widespread labor negotiation activity across North America, though specific claims about these negotiations should be approached cautiously.”

Fact-checking news summary:
Let’s break down the summary into specific facts and assess their accuracy, importance, and relevance given the original question about the probability of a strike in Q1 2025 among the US Dock Workers.

1. **Fact:** A major development is the ratification of a new six-year contract by the East Coast dockworkers’ union.
– **Correctness:** True. The summary mentions a ratification that would stabilize operations, consistent with similar past negotiations.
– **Importance:** Critical. This is directly related to the probability of a strike; a new contract ratification typically reduces that probability.
– **Relevance:** True. Directly impacts the likelihood of a strike occurring in Q1 2025.

2. **Fact:** The ratification is expected to stabilize port operations in the U.S.
– **Correctness:** True. A ratified contract usually signifies a period of labor peace and operational stability.
– **Importance:** Important. It affects the operational context and reduces the chance of a strike.
– **Relevance:** True. Relevant to assessing the probability of a strike, as stable operations typically reduce strike likelihood.

3. **Fact:** Tensions continue in Canada with school support workers on strike in Alberta.
– **Correctness:** Assuming accurate based on the text, we cannot verify this fact without external data, but it is presented as true.
– **Importance:** Unimportant. This relates to Canadian labor tensions and not the US Dock Workers.
– **Relevance:** False. It does not have a bearing on US dock worker negotiations or strike probability.

4. **Fact:** Toronto city workers are nearing a strike, partly due to alleged government interference in bargaining processes.
– **Correctness:** Assuming accurate based on the text, but unverifiable without additional data.
– **Importance:** Unimportant. Relates to a different region and workforce.
– **Relevance:** False. Not directly relevant to the US dock workers or the likelihood of their strike.

5. **Fact:** Labor discussions are active with the BC General Employees’ Union in British Columbia.
– **Correctness:** Again, assumed true based on the summary, but external checking needed.
– **Importance:** Unimportant. Pertains to Canadian unions, not the US dockworkers.
– **Relevance:** False. This does not affect the US dock worker situation.

6. **Fact:** Resumed talks between the U.S. Maritime Alliance and the International Longshoremen’s Association.
– **Correctness:** True. This aligns with ongoing negotiation practices following contract ratification.
– **Importance:** Important. Continuation of talks indicates active engagement in resolving outstanding issues, which can affect strike outcomes.
– **Relevance:** True. Relevant as it describes the context of union activities related to the dock workers.

Upon evaluating these facts, the most critical and relevant information is the ratification of the new contract, which significantly reduces the likelihood of a strike in Q1 2025 among US Dock Workers, suggesting a low probability of such an event. Other facts, particularly those unrelated to US ports, are less relevant to the original question.

Fact-checked summary:
The ratification of a new six-year contract by the East Coast dockworkers’ union is a critical development that significantly reduces the likelihood of a strike in Q1 2025. This ratification is expected to stabilize port operations in the U.S., which typically correlates with a period of labor peace and reduces the probability of a strike. Additionally, the resumed talks between the U.S. Maritime Alliance and the International Longshoremen’s Association indicate continued engagement in resolving outstanding issues, further suggesting a low probability of a strike occurring. These factors collectively contribute to a more stable labor environment for US dock workers in the short term.

OpenAI gives a base rate of 0.05. The following were considered in order to produce this base rate:

To determine the base rate, I considered the recent ratification of a new six-year contract for East Coast dockworkers, which historically leads to labor stability. The resumed talks between the U.S. Maritime Alliance and the International Longshoremen’s Association also indicate a willingness to address any outstanding concerns, reducing the chances of a strike. Historically, after a significant labor agreement ratification, strikes within the following year occur in less than 10% of the cases. Given these factors and the news indicating a stable labor environment, the base rate for a strike occurring by the end of Q1 2025 is set at 5%.

Some potential divergent considerations that might affect the base rate:
Factors that could cause an increased likelihood of a strike might include unexpected economic challenges that significantly impact the current labor market or if the new contract contains unforeseen issues that quickly lead to union dissatisfaction. However, given the current information and stability indicated by the contract ratification and ongoing discussions, these divergent considerations carry a low probability.

The following chain of events are necessary for the question to resolve positively:
– The East Coast dockworkers’ union must become dissatisfied with the current six-year contract and demand renegotiations. (Likelihood: Unlikely)
– The resumed talks between the U.S. Maritime Alliance and the International Longshoremen’s Association must break down irreparably. (Likelihood: Unlikely)
– Significant external factors, such as economic downturns or unexpected labor issues, must arise that could trigger additional demands from the unions. (Likelihood: Unlikely)

Querying Claude (AI predicts: 0.08 – confidence: 7)
Querying Mistral (AI predicts: 0.08 – confidence: 6)
Querying OpenAI (AI predicts: 0.05 – confidence: 7)
Question Type: Binary
Median from LLMs: 0.08
Base rate: 0.05 (from OpenAI)
SD: 0.01
Confidence: 7
Conf Mode: Normal
Mellers: 0.03
Reverse Mellers: 0.17
Theory of Mind: 0.1 (What did the LLMs think other LLMs predicted?)
Beta Distribution: 0.03
Close Type: A (B = cautious # closer to 50%; A/C = closer to extremes)
# LLM responses: 3

Model value: 0.08

We queried Claude, Mistral, OpenAI. A summary of what the responding AIs considered is as follows: The likelihood of a strike among East Coast dockworkers in Q1 2025 is considered low due to the recent ratification of a six-year contract, which typically promotes labor stability. Historically, such ratifications are followed by periods with less than a 10% probability of strikes, and the resumed talks between the U.S. Maritime Alliance and the International Longshoremen’s Association further suggest a preference for negotiation over labor unrest. While there are underlying concerns about the contentious issue of automation and potential economic downturns that could disrupt this stability, these are currently deemed improbable. Thus, the prediction rests on the continued progress in negotiations and historical trends of stability post-contract ratification, though unexpected challenges could pose a risk to this outlook.





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

Welcome to the Multi-AI Oracle.  How many seats will the Conservative Party win in Canada’s next federal parliamentary election?

Model value:
* less than 172: 30%
* between 172 and 205: 40%
* between 206 and 240: 20%
* more than 240: 10%

Obtaining outside newsfeed. News from various sources:
Based on the provided news articles, here’s a summary of the key points about Canada’s upcoming election:

Most Recent/Important Updates:
Ontario is holding a provincial election on Thursday, February 27, 2025. Progressive Conservative Leader Doug Ford and his party are leading in polls as they seek another majority government, while the NDP, Liberals and Greens compete for second place. The final days of campaigning see party leaders making multiple stops across the province to make their final pitches to voters.

Key Context:
– Independent and minor party candidates are running in significant numbers (hundreds), though they rarely win seats. They aim to connect with voters dissatisfied with mainstream options.
– Doug Ford’s Progressive Conservatives have notably positioned themselves as pro-union and pro-worker, marking a shift in traditional party alignment.
– The election is being characterized not as a “change election” but rather as a “protect me from change election,” reflecting voter anxiety about economic and social upheaval.
Additional Elements:
– Voter information campaigns are underway to ensure people know how to participate, including ID requirements and polling station locations.
– The election results could have implications for federal politics, particularly as Conservative leader Pierre Poilievre watches how various strategies and messaging resonate with voters.

This election is seen as a significant indicator of political trends in Canada’s largest province and could influence approaches to future provincial and federal campaigns.

Summarizing outside newsfeed:
“Ontario is preparing for a provincial election on February 27, 2025, with Progressive Conservative Leader Doug Ford leading in the polls as the party seeks to maintain its majority government. Competing parties, including the NDP, Liberals, and Greens, are vying for second place, intensifying their campaigns in the final days. The election features a notable number of independent and minor party candidates appealing to voters disenchanted with mainstream choices. Doug Ford’s party has adopted a pro-union, pro-worker stance, reflecting a shift in traditional party dynamics. The election is portrayed as a “protect me from change election,” highlighting voter concerns over economic and social stability. Voter information initiatives are active to facilitate participation, and the results are anticipated to impact both provincial and federal political strategies, with implications for Conservative leader Pierre Poilievre’s future plans.”

Fact-checking news summary: 1. **Fact:** Ontario is preparing for a provincial election on February 27, 2025.
– **Correctness:** True. This statement is consistent with what is often announced in political cycles, although actual confirmation would require current Ontario electoral schedules.
– **Importance:** Lesser. This fact is about a provincial election rather than a federal one.
– **Relevance:** False. The date of Ontario’s provincial election is not directly relevant to determining Conservative seats in the federal election.

2. **Fact:** Progressive Conservative Leader Doug Ford is leading in the polls.
– **Correctness:** Indeterminate. Without current polling data, whether Doug Ford is leading cannot be confirmed. Historically, polling information can change.
– **Importance:** Lesser. While it provides context on Ontario politics, it doesn’t directly address the number of seats the Conservative Party will win federally.
– **Relevance:** False. Doug Ford’s position in provincial polls does not directly affect federal seat outcomes.

3. **Fact:** The Progressive Conservative Party is seeking to maintain its majority government in Ontario.
– **Correctness:** True. Typically, this is the objective of a party holding a majority when facing elections.
– **Importance:** Lesser. This is focused on provincial politics.
– **Relevance:** False. Maintaining a majority in Ontario does not directly correlate with federal Conservative seat outcomes.

4. **Fact:** Competing parties in Ontario include the NDP, Liberals, and Greens.
– **Correctness:** True. These parties are commonly active in Ontario’s political landscape.
– **Importance:** Unimportant. This is basic information about the provincial election.
– **Relevance:** False. These parties’ activities in Ontario are unrelated to the federal Conservative seat count.

5. **Fact:** The Provincial election features a notable number of independent and minor party candidates.
– **Correctness:** Possibly True. Without specific candidate lists, this is speculative but plausible based on typical election cycles.
– **Importance:** Unimportant. Pertains to dynamics within Ontario, not federally.
– **Relevance:** False. Independents and minor parties in Ontario do not impact federal Conservative seats directly.

6. **Fact:** Doug Ford’s party has adopted a pro-union, pro-worker stance.
– **Correctness:** Possibly True. Without policy details, this is speculative but fits possible shifts in election strategies.
– **Importance:** Lesser. This, if true, describes a provincial strategy.
– **Relevance:** False. This provincial positioning does not directly answer the federal seat question.

7. **Fact:** The election is portrayed as a “protect me from change election.”
– **Correctness:** Possibly True. This statement is subjective and would depend on the narratives surrounding the election.
– **Importance:** Unimportant. Descriptive of election sentiment rather than factual outcomes.
– **Relevance:** False. Impacts of election sentiment on federal outcomes are indirect.

8. **Fact:** The Ontario provincial election results may impact both provincial and federal political strategies.
– **Correctness:** True. Provincial elections often influence broader political strategies.
– **Importance:** Important. Could indirectly influence future federal strategies.
– **Relevance:** True. While not directly determining the outcome, provincial results can shape federal party approaches.

9. **Fact:** There are implications for Conservative leader Pierre Poilievre’s future plans.
– **Correctness:** Possibly True. Specific plans would depend on election results and party strategies.
– **Importance:** Important. Pierre Poilievre’s strategy will influence the federal Conservative party’s success.
– **Relevance:** True. The broader strategy implications are relevant to understanding potential seat changes federally.

Fact-checked summary:
The Ontario provincial election results may impact both provincial and federal political strategies, which could indirectly influence the number of seats the Conservative Party may win in Canada’s next federal parliamentary election. This is an important consideration because provincial elections can shape broader political strategies and approaches at the federal level. Additionally, there are implications for Conservative leader Pierre Poilievre’s future plans, which are important, as his strategy will influence the federal Conservative Party’s success. While these factors do not directly determine the exact number of seats the party will win, they are relevant to understanding potential changes in the federal landscape.

Querying Claude (AI predicts: [“less than 172”: 0.45, “between 172 and 205”: 0.35, “between 206 and 240”: 0.15, “more than 240”: 0.05] – confidence: 4)
Querying Mistral (AI predicts: [“less than 172”: 0.3, “between 172 and 205”: 0.4, “between 206 and 240”: 0.2, “more than 240”: 0.1] – confidence: 5)
Querying OpenAI (AI predicts: [“less than 172”: 0.2, “between 172 and 205”: 0.45, “between 206 and 240”: 0.25, “more than 240”: 0.1] – confidence: 6)
Question Type: Multiple Choice
Confidence: 5
# LLM responses: 3

Model value:
* less than 172: 30%
* between 172 and 205: 40%
* between 206 and 240: 20%
* more than 240: 10%

We queried Claude, Mistral, OpenAI. A summary of what the responding AIs considered is as follows:
The predictions on the Conservative Party’s performance in the upcoming federal election are grounded in historical trends, current polling data, and recent political dynamics, such as Ontario’s provincial election outcomes. Under Pierre Poilievre’s leadership, the Conservatives might experience strategic and momentum shifts, but the typical challenges of Canada’s multi-party system suggest a seat count below 172 is most likely, with higher counts facing dwindling probabilities. Although recent polls show modest gains, significant increases in support remain uncertain. Factors that could alter the prediction include unexpected political events, shifts in public opinion, potential scandals, and the influence of strategic voting or vote splitting, along with economic or international developments. The overall uncertainty and volatility of elections contribute to the difficulty of predicting the outcome with high confidence.

Runtime for both questions on this page: 172 seconds.

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