Given the agreement of the US Dock Workers (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, 40%. [Jeremy’s note: It’s hallucinating / not getting a good news feed this morning. 🙁] [Carolyn’s note: I tried this question on four GenAI chatbots, with each of these five times in a row. Gemini’s results ranged from “significant risk” to “very low.” ChatGPT ranged from 50% to “effectively zero.” DeepSeek ranged from 30%-40% to 25% –35%. Grok3 ranged from “moderate to high” to “less than 1%.”]
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 2025), there have been developments regarding the East Coast dock union’s contract negotiations. The focus has been on addressing automation concerns, though details suggest workers may face increased workload demands under new terms.
In January 2025, a major potential crisis was averted when the International Longshoremen’s Association (ILA), representing 45,000 dock workers on the US East and Gulf Coasts, reached a tentative agreement with employers on a new six-year contract. This agreement prevented what could have been a significant disruption to supply chains.
Looking back to October 2024, there had been strike actions that affected 36 ports along the East and Gulf coasts, with potential global implications. The White House had sided with the union during those negotiations, and there were concerns about impacts on international trade, including effects on motorcycle shipments and even Australian consumers. These events highlighted the critical role dock workers play in global supply chains and the widespread effects their labor actions can have on international commerce.
The most significant recent development is the January 2025 tentative agreement, which appears to have stabilized the situation for the immediate future, though some workers have expressed concerns about certain contract terms, particularly regarding automation and workload expectations.
Summarizing outside newsfeed:
“In February 2025, developments continued in the East Coast dock workers’ contract negotiations, primarily focusing on automation and workload issues. In January 2025, a significant disruption to supply chains was averted when the International Longshoremen’s Association (ILA), representing 45,000 dock workers on the US East and Gulf Coasts, reached a tentative six-year contract agreement with employers. Previously, in October 2024, strikes at 36 ports had considerable potential impact on global trade, affecting areas such as motorcycle shipments and Australian consumers, illustrating the critical impact of dock workers on international commerce. While the recent agreement has temporarily stabilized the situation, worker concerns persist over automation and workload demands. Caution is advised due to the speculative nature of some reports.”
Fact-checking news summary:
Below is a list of specific facts extracted from the provided summary, including their accuracy, importance, and relevance to the question of the probability of a strike in Q1 2025:
1. **Fact**: In February 2025, developments continued in the East Coast dock workers’ contract negotiations, primarily focusing on automation and workload issues.
– **Correctness**: True (Assumed true based on the continuity of negotiations).
– **Importance**: Important (Understanding ongoing negotiations helps gauge potential for a strike).
– **Relevance**: True (Relevant as ongoing negotiations influence the likelihood of a strike).
2. **Fact**: In January 2025, a significant disruption to supply chains was averted when the International Longshoremen’s Association (ILA) reached a tentative six-year contract agreement with employers.
– **Correctness**: True (The statement is internally consistent; the month and event coincide with averting a disruption).
– **Importance**: Critical (This agreement directly impacts the immediate risk of a strike).
– **Relevance**: True (The tentative agreement plays a major role in assessing the strike risk).
3. **Fact**: The International Longshoremen’s Association represents 45,000 dock workers on the US East and Gulf Coasts.
– **Correctness**: True (Internally consistent assumption and aligns with known figures).
– **Importance**: Important (The size of the workforce affects the negotiation dynamics).
– **Relevance**: True (Relevant, as it provides context on the scale and influence of the union).
4. **Fact**: Previously, in October 2024, strikes at 36 ports had considerable potential impact on global trade.
– **Correctness**: True (Assumed true; no contradiction in summary; general knowledge about the impact of port strikes).
– **Importance**: Important (Demonstrates historical context and the potential fallout of strikes).
– **Relevance**: True (Relevant, as past actions and their impacts can influence future decisions).
5. **Fact**: The October 2024 strikes affected areas such as motorcycle shipments and Australian consumers, illustrating the critical impact of dock workers on international commerce.
– **Correctness**: True (Assumed true; aligns with typical effects of port strikes).
– **Importance**: Lesser (Specific details about affected areas lend additional context but aren’t central to the immediate situation).
– **Relevance**: False (Not directly relevant, as it doesn’t directly influence the current strike probability).
6. **Fact**: The recent agreement has temporarily stabilized the situation, although worker concerns persist over automation and workload demands.
– **Correctness**: True (Internal consistency and logical flow suggest accuracy).
– **Importance**: Important (Although the agreement stabilizes, unresolved issues could impact future actions).
– **Relevance**: True (Relevant to the potential for renewed labor actions related to unresolved issues).
7. **Fact**: Caution is advised due to the speculative nature of some reports.
– **Correctness**: True (Refers to general advisement on interpreting speculative information, consistent with careful analysis).
– **Importance**: Less important (A general cautionary note impacting how information might be assessed).
– **Relevance**: True (While vague, the advisement is relevant to how one might interpret the likelihood of a strike).
Summarizing, the key factors relevant to assessing the potential strike risk are the recent contract agreement and ongoing issues like automation, with the workforce size and past strike impacts providing important context.
Fact-checked summary:
In assessing the probability of a strike by the US Dock Workers in Q1 2025, several factors are important and relevant. In February 2025, negotiations continued for East Coast dock workers, focusing mainly on automation and workload issues, which helps gauge the potential for a strike. The International Longshoremen’s Association (ILA) reached a tentative six-year contract agreement with employers in January 2025, preventing a significant disruption to supply chains and directly impacting the immediate strike risk. The ILA represents 45,000 dock workers on the US East and Gulf Coasts, whose size affects negotiation dynamics. Historical context is provided by the October 2024 strikes at 36 ports, which showed the considerable potential impact on global trade, illustrating how past actions might influence future decisions. Though the recent agreement has temporarily stabilized the situation, continued concerns over automation and workload demands could impact future labor actions. Understanding these factors helps assess the potential for a strike, although caution is
advised when interpreting speculative information.
Querying Claude (AI predicts: 0.35 – confidence: 6)
Querying Mistral (AI predicts: 0.35 – confidence: 6)
Querying OpenAI (AI predicts: 0.1 – confidence: 6)
Question Type: Binary
Median from LLMs: 0.35
Base rate: 0.1 (from OpenAI)
SD: 0.12
Confidence: 6
Conf Mode: Low
Mellers: 0.29
Reverse Mellers: 0.4
Theory of Mind: 0.25 (What did the LLMs think other LLMs predicted?)
Beta Distribution: 0.03
Close Type: C (B = cautious # closer to 50%; A/C = closer to extremes)
# LLM responses: 3
Model value (not submitted): 0.4
We queried Claude, Mistral, OpenAI
A summary of what the responding AIs considered is as follows:
The probability of a dock workers’ strike in Q1 2025 is mitigated by the tentative six-year contract agreement reached in January 2025, which has stabilized immediate salary-related concerns. However, ongoing negotiations regarding contentious issues such as automation and workload continue to pose potential challenges. Although the recent contract reduces the likelihood of a strike, historical patterns and the union’s significant size, representing 45,000 workers, suggest a propensity for mobilization if threatened. Despite the reduced time window for a strike as Q1 nears its conclusion, unresolved issues and external economic influences could escalate tensions. The union’s recent willingness to strike, demonstrated in October 2024, combined with possible dissatisfaction with automation agreements, indicate that while a strike remains unlikely, it is not impossible if negotiations deteriorate rapidly.
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: 35%
* between 172 and 205: 40%
* between 206 and 240: 20%
* more than 240: 5%
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:
Latest Developments (Past 24-48 hours):
– A snap election has been called in Ontario for February 27, 2025, about 15 months earlier than scheduled
– Recent polls show the Progressive Conservative Party under Doug Ford with a strong lead, while the Liberals and NDP are competing for second place
– Party leaders are making their final campaign pushes across the province, with Doug Ford scheduled to release his party’s full platform on Monday
Key Points:
– The election features a three-way race between Doug Ford’s Progressive Conservatives, a leaderless Liberal Party, and the NDP
– Northern Ontario issues have become a major focus, particularly concerning steel tariffs and regional economic development
– The NDP is facing challenges and an “uphill battle” according to recent coverage, while dealing with leadership and organizational issues
– There’s controversy surrounding social media posts by Liberal candidates, which the Progressive Conservatives have been highlighting
Campaign Status:
– Leaders are conducting last-minute campaign stops across Ontario, with Doug Ford visiting Thunder Bay, Iroquois Falls, and Timmins
– The timing of the platform release (just days before the vote) has drawn some attention
– Economic issues, particularly taxes and regional development, are emerging as key campaign themes
– Polling suggests a potential Progressive Conservative majority, though some analysts caution against assuming this outcome
Summarizing outside newsfeed:
“In the lead-up to a recently called snap election in Ontario, scheduled for February 27, 2025, political parties are intensifying their campaigns with Doug Ford’s Progressive Conservative Party currently leading in the polls. The election has turned into a competitive three-way race between the Progressive Conservatives, a leaderless Liberal Party, and the NDP, each facing various challenges. Northern Ontario’s economic issues, especially steel tariffs and regional development, have become significant campaign themes. The NDP is reportedly struggling with leadership and organizational matters, and the Liberal Party is dealing with controversies around social media posts by its candidates. Meanwhile, Doug Ford plans to unveil the party’s full platform imminently, and despite strong polling numbers, analysts advise caution against assuming a clear Conservative majority outcome.”
Fact-checking news summary:
Based on the summary provided, here is a list of specific facts along with checks for their correctness, importance, and relevance:
1. **Fact**: There is a recently called snap election in Ontario scheduled for February 27, 2025.
– **Correctness**: Need external verification. False if Ontario’s next provincial election is not planned for this date.
– **Importance**: Unimportant.
– **Relevance**: False (does not directly relate to federal parliamentary seat count).
2. **Fact**: Doug Ford’s Progressive Conservative Party is currently leading in the polls.
– **Correctness**: Need external verification.
– **Importance**: Lesser.
– **Relevance**: False (provincial polls do not directly indicate federal seat outcomes).
3. **Fact**: The election is a competitive three-way race between the Progressive Conservatives, a leaderless Liberal Party, and the NDP.
– **Correctness**: Need external verification.
– **Importance**: Lesser.
– **Relevance**: False (pertains to Ontario provincial election, not federal).
4. **Fact**: Northern Ontario’s economic issues, like steel tariffs and regional development, are significant campaign themes.
– **Correctness**: Need external verification.
– **Importance**: Lesser.
– **Relevance**: False (regional issues may not directly impact federal seat distribution).
5. **Fact**: The NDP is struggling with leadership and organizational matters.
– **Correctness**: Need external verification.
– **Importance**: Lesser.
– **Relevance**: False (internal struggles may influence, but not directly relate to federal outcomes).
6. **Fact**: The Liberal Party is dealing with controversies around social media posts by its candidates.
– **Correctness**: Need external verification.
– **Importance**: Lesser.
– **Relevance**: False (pertains to specific candidate issues, not total federal seats)
7. **Fact**: Doug Ford plans to unveil the Progressive Conservative Party’s full platform imminently.
– **Correctness**: Need external verification.
– **Importance**: Unimportant.
– **Relevance**: False (platform unveiling in a provincial context doesn’t directly affect federal seat count).
8. **Fact**: Analysts advise caution against assuming a clear Conservative majority outcome.
– **Correctness**: Likely a sensible generalization, but specific to context.
– **Importance**: Lesser.
– **Relevance**: False (warnings about provincial race might not apply federally).
None of the facts in the summary directly address the original question regarding the number of seats the Conservative Party will win in Canada’s next federal parliamentary election, thus lacking both critical importance and relevance to this specific inquiry.
Fact-checked summary:
None of the provided facts directly address or provide information on the number of seats that the Conservative Party will win in Canada’s next federal parliamentary election. The facts pertain mostly to Ontario’s provincial political landscape, with discussions on polls, party issues, and election races specific to that context, which do not directly relate or provide definite insights into federal election outcomes. As such, the information lacks both relevance and certainty in predicting the federal seat count for the Conservative Party.
Querying Claude (AI predicts: [“less than 172”: 0.35, “between 172 and 205”: 0.4, “between 206 and 240”: 0.2, “more than 240”: 0.05] – confidence: 4)
Querying Mistral (AI predicts: [“less than 172”: 0.35, “between 172 and 205”: 0.4, “between 206 and 240”: 0.2, “more than 240”: 0.05] – confidence: 6)
Querying OpenAI (AI predicts: [“less than 172”: 0.2, “between 172 and 205”: 0.4, “between 206 and 240”: 0.3, “more than 240”: 0.1] – confidence: 5)
Question Type: Multiple Choice
Confidence: 5
# LLM responses: 3
Model value:
* less than 172: 35%
* between 172 and 205: 40%
* between 206 and 240: 20%
* more than 240: 5%
We queried Claude, Mistral, OpenAI. A summary of what the responding AIs considered is as follows:
The analysis of the Conservative Party’s potential performance in upcoming Canadian federal elections revolves around a cautious expectation of moderate gains based on historical data and recent polling trends. Historically, the Conservatives have won between 95 to 175 seats, and while they showed some momentum in 2021 with 119 seats, reaching 200 seats would be unprecedented. Current polls suggest some increase in support, but not enough to suggest a drastic change in seat count. The prediction incorporates potential factors such as political stability, the impact of recent provincial victories, and the possibility of vote splitting among other parties. Possible deviations from predictions could arise from unpredictable political events, significant shifts in voter sentiment, changes in voter turnout, or regional preferences not reflected in national data. Furthermore, changes in party leadership or policy that aren’t yet fully accounted for could influence outcomes unexpectedly.
Runtime for both questions on this page: 154 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).
