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, 35%.
Obtaining outside newsfeed. News from various sources. Based on the most recent news articles, here’s a summary of the US dockworkers situation:
Most Recent: Montreal Port Workers Strike (2 days ago)
Longshoremen at the Port of Montreal are planning an indefinite strike starting Thursday morning if a deal isn’t reached with the Maritime Employers Association (MEA). This follows several limited work stoppages at the port. The dispute involves negotiations between the MEA and CUPE Longshoremen’s Union, Local 375.
Toronto City Workers (5 days ago)
CUPE Local 79, representing approximately 30,000 Toronto city workers, has moved closer to a potential strike after filing a “no board” request. The affected sectors include critical services such as public health, planning, City Hall operations, employment and social services, ambulance dispatch, child care, and 311 services.
Bangladesh Port Strike (7 days ago)
While the strike at Chittagong Port has ended, there are ongoing challenges with significant backlogs of containers, TEUs (Twenty-foot Equivalent Units), and ships, particularly concerning as the Muslim holy month of Ramadan approaches. The aftermath of the strike continues to impact port operations and logistics.
These labor actions reflect a broader pattern of worker mobilization in various port and municipal sectors across different regions, with potential impacts on global supply chains and local services.
Summarizing outside newsfeed:
“Recent labor actions have highlighted a pattern of worker mobilization in port and municipal sectors across different regions. Notably, longshoremen at the Port of Montreal are planning an indefinite strike due to stalled negotiations with the Maritime Employers Association, following several prior work stoppages. Additionally, CUPE Local 79 in Toronto has moved toward a potential strike affecting critical city services. Meanwhile, despite the resolution of a strike at Bangladesh’s Chittagong Port, challenges persist with backlogs affecting operations, particularly with the approach of Ramadan. These developments may have implications for global supply chains and local services, although the reliability of these reports should be carefully considered.”
Fact-checking news summary:
To assess the probability of a strike in Q1 2025 for the US Dock Workers (International Longshoremen’s Association), we review the provided summary and extract specific facts. Each fact is evaluated for correctness, importance, and relevance to the question on the probability of a strike:
1. **Fact**: Longshoremen at the Port of Montreal are planning an indefinite strike due to stalled negotiations with the Maritime Employers Association.
– Correctness: True. Labor disputes at the Port of Montreal have occurred, and it’s feasible for them to plan a strike.
– Importance: Important. Demonstrates a pattern of unrest in the port sector, which may influence the International Longshoremen’s Association’s actions.
– Relevance: True. The situation in Montreal could impact or serve as leverage in negotiations at US ports.
2. **Fact**: Several prior work stoppages have occurred at the Port of Montreal.
– Correctness: True. Historically, the Port of Montreal has experienced work stoppages, lending credibility to planned future actions.
– Importance: Important. Indicates ongoing labor tensions in the industry, relevant to assessing strike risk.
– Relevance: True. Contextualizes labor conditions relevant to the US dockworkers’ situation.
3. **Fact**: CUPE Local 79 in Toronto has moved toward a potential strike affecting critical city services.
– Correctness: True. CUPE Local 79 has mobilized in past for labor actions, making this plausible.
– Importance: Lesser. While it indicates regional labor activity, it’s less directly related to US dockworkers at the ports.
– Relevance: False. Indirectly affects port negotiations, but not directly relevant.
4. **Fact**: A strike was resolved at Bangladesh’s Chittagong Port, but challenges persist with backlogs affecting operations, particularly with the approach of Ramadan.
– Correctness: True. Chittagong Port frequently experiences operational challenges.
– Importance: Unimportant. International events have low direct impact on US port negotiations.
– Relevance: False. Little to no direct connection to US dockworkers’ negotiations.
5. **Fact**: Recent labor actions highlight a pattern of worker mobilization in port and municipal sectors across different regions.
– Correctness: True. Labor mobilization trends are visible globally.
– Importance: Important. Such patterns in labor activity may affect perceptions and strategies of US dockworkers.
– Relevance: True. Underpins the context of increased potential for labor action.
6. **Fact**: These developments may have implications for global supply chains and local services, although the reliability of these reports should be carefully considered.
– Correctness: True. Labor actions often affect supply chains, though the note on reliability suggests potential caution in interpretation.
– Importance: Important. Understanding impacts on supply chains can give insight into bargaining strengths or pressures during negotiations.
– Relevance: True. Relevant to contextual understanding of bargaining positions and potential strike impacts.
In conclusion, facts related to global or regional labor mobilizations (facts 1, 2, and 5) hold higher importance and relevance when considering the risk of a strike by the US Dock Workers in Q1 2025. They suggest a general atmosphere of labor unrest, which could influence the probability of a strike if issues like automation and scheduling remain unresolved at the bargaining table.
Fact-checked summary:
To assess the probability of a strike by the US Dock Workers (International Longshoremen’s Association) in Q1 2025, it is important to consider facts that are both true and relevant to the situation. Firstly, longshoremen at the Port of Montreal are planning an indefinite strike due to stalled negotiations with the Maritime Employers Association, highlighting unrest in the port sector, which may influence negotiations for US dockworkers. Historical occurrences of work stoppages at the Port of Montreal further underscore ongoing labor tensions. Additionally, there is a global trend of worker mobilization within port and municipal sectors, which is crucial in understanding the US dockworkers’ context. These facts suggest an atmosphere of labor unrest, implying a heightened risk of a strike if critical issues like automation and scheduling are not addressed in the negotiations.
OpenAI gives a base rate of 0.25. The following were considered in order to produce this base rate:
The base rate of 0.25 is derived from the historical frequency of strikes by dockworkers in the United States, coupled with current labor trends. Historically, major strikes in this sector are infrequent due to the significant economic stakes and often successful mediation efforts. However, the similarity of grievances and recent escalations in the sector at international levels could increase the likelihood of a strike. Consideration is given to the fact that many labor negotiations, especially in critical sectors, involve brinkmanship but are resolved without work stoppages.
Some potential divergent considerations that might affect the base rate:
Factors that could reduce the likelihood from the base rate include the successful intervention of federal mediators and the high economic cost of a strike, which incentivizes resolution. Conversely, if automation and working condition negotiations were to stall significantly or if similar successes of worker movements in other regions (e.g., Montreal) inspire more assertive union action, the probability could increase. Additionally, unforeseen political or economic pressures could influence the likelihood of a strike at any moment leading up to Q1 2025.
The following chain of events are necessary for the question to resolve positively:
– The ongoing contract negotiations between the International Longshoremen’s Association (ILA) and the US Maritime Alliance (USMX) must fail to reach a satisfactory agreement for both parties within a reasonable timeframe. Likelihood: Moderate.
– There must be an alignment of grievances among the US dockworkers similar to those of the Montreal port workers, such as automation and scheduling issues. Likelihood: Moderate to High.
– A failure in mediation efforts or intervention strategies, including those by federal mediators, which are often brought in to prevent strikes in critical economic sectors like shipping. Likelihood: Low to Moderate.
– A decision by ILA leadership to call a strike, with sufficient worker support to execute a work stoppage. Likelihood: Moderate.
Querying Claude (AI predicts: 0.35 – confidence: 6)
Querying Mistral (AI predicts: 0.45 – confidence: 6)
Querying OpenAI (AI predicts: 0.3 – confidence: 6)
Question Type: Binary
Median from LLMs: 0.35
Base rate: 0.25 (from OpenAI)
SD: 0.06
Confidence: 6
Conf Mode: Normal
Mellers: 0.29
Reverse Mellers: 0.4
Theory of Mind: 0 (What did the LLMs think other LLMs predicted?)
Beta Distribution: 0.06
Close Type: B (B = cautious # closer to 50%; A/C = closer to extremes)
# LLM responses: 3
Model value: 0.35
We queried Claude, Mistral, OpenAI. A summary of what the responding AIs considered is as follows:
The reasoning across the various AI summaries indicates that the likelihood of a US dockworker strike in Q1 2025 is influenced by a mix of historical trends, current labor negotiations, and regional labor unrest. Historically, strikes are not frequent, with a baseline probability of 0.25, but current contentious issues, particularly surrounding automation, slightly raise the risk. Recent salary agreements suggest some progress, which, along with previous successful mediation efforts, could mitigate the risk of a strike. However, factors such as the continuing global trend of worker mobilization and recent labor tensions, exemplified by strikes at the Port of Montreal, are contributing to an elevated concern. These dynamics are weighed against high economic stakes and the typically successful role of federal mediators in resolving such disputes. Nonetheless, the scenario remains complex, as unexpected internal and external dynamics could alter the course of ongoing negotiations.
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: 45%
* between 172 and 205: 35%
* between 206 and 240: 15%
* 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:
Most Recent Developments:
– Advance voting has opened for Ontario’s local election, though with fewer days available than in previous elections due to an early campaign schedule. Party leaders are making campaign stops in the Greater Toronto Area and Kitchener region.
– Recent polling shows significant movement in federal party support:
– The Conservative Party leads with 41% support
– Liberals follow with 33% support
– The NDP is experiencing what’s described as a “deadly slide” in polls
– Pierre Poilievre, Conservative leader, has an unfavorability rating of 56% despite his party’s lead
Important Context:
Pierre Poilievre, who had previously aligned himself with MAGA-style politics, is now distancing himself from Donald Trump, particularly regarding Trump’s comments about NATO and potential tariffs on Canada. This shift comes as polls show tight races and high unfavorability ratings for Poilievre personally, even as his party maintains a lead in national polling.
In Ontario’s provincial politics, advance voting for local elections has begun, with candidates focusing on key issues like healthcare, housing affordability, and economic concerns. The election features several competitive ridings, including traditionally Conservative strongholds that are now seeing more contested races.
Summarizing outside newsfeed:
“Recent developments in Canadian politics reveal that Ontario’s local elections have begun advance voting with reduced days due to an earlier campaign schedule, as party leaders focus their efforts in key areas like the Greater Toronto Area. Federal polling indicates a lead for the Conservative Party at 41%, followed by the Liberals at 33%, while the NDP’s support appears to be declining significantly. Despite the Conservative Party’s lead, their leader, Pierre Poilievre, faces a high unfavorability rating of 56% and is reportedly distancing himself from former U.S. President Donald Trump’s rhetoric, particularly on issues involving NATO and tariffs. In Ontario, pivotal election issues such as healthcare, affordable housing, and economic challenges are at the forefront of candidate discussions, with previously secure Conservative ridings now potentially more competitive. It is crucial to verify these reports, as the newsfeed may contain unverified claims and propaganda.”
Fact-checking news summary:
Based on the summary provided, here is a list of specific facts along with an assessment of their correctness, importance, and relevance to the resolution of the question “How many seats will the Conservative Party win in Canada’s next federal parliamentary election?”:
1. **Fact:** Ontario’s local elections have begun advance voting with reduced days due to an earlier campaign schedule.
– **Correctness:** True (Internally consistent; typically, elections can alter schedules based on campaign periods)
– **Importance:** Lesser importance (Local election procedures in Ontario have limited impact on federal seat outcomes)
– **Relevance:** False (Not directly relevant to predicting federal election outcomes)
2. **Fact:** Party leaders are focusing efforts in the Greater Toronto Area.
– **Correctness:** True (The Greater Toronto Area is a key battleground in Canadian elections)
– **Importance:** Important (Affects federal election strategy and potentially seat outcomes)
– **Relevance:** True (Relevant to understanding strategic electoral focus areas)
3. **Fact:** Federal polling indicates the Conservative Party is leading at 41%.
– **Correctness:** Needs verification (Polling data can vary, requiring current and reliable sources)
– **Importance:** Critical (Directly relates to the potential number of seats the Conservative Party may win)
– **Relevance:** True (Critical to the question of seat winning)
4. **Fact:** The Liberals are at 33% in the federal polling.
– **Correctness:** Needs verification (Same as above; polling data must be current and accurate)
– **Importance:** Important (Impacts predictions about electoral outcomes)
– **Relevance:** True (Relevant to predicting election outcomes)
5. **Fact:** The NDP’s support is declining significantly.
– **Correctness:** Needs verification (Polling trends fluctuate and require checking)
– **Importance:** Important (Shifts in NDP support can influence seat distribution among other parties)
– **Relevance:** True (Can alter Conservative Party’s seat results indirectly)
6. **Fact:** Pierre Poilievre’s unfavorability rating is at 56%.
– **Correctness:** Needs verification (Subject to change; polling on favorability can vary)
– **Importance:** Important (Leaders’ favorability can impact party success in elections)
– **Relevance:** True (Relevant as leadership perceptions affect party performance)
7. **Fact:** Poilievre is distancing himself from Donald Trump’s rhetoric on NATO and tariffs.
– **Correctness:** Needs verification (Relies on current political strategy narratives)
– **Importance:** Lesser importance (May affect public perception but less directly tied to seat outcomes)
– **Relevance:** True (Somewhat relevant as it can influence voter sentiment)
8. **Fact:** Healthcare, affordable housing, and economic challenges are key election issues in Ontario.
– **Correctness:** True (Consistent with common major electoral issues)
– **Importance:** Important (Issues can affect voter turnout and preferences)
– **Relevance:** True (Relevant as issues drive voter decision-making)
9. **Fact:** Previously secure Conservative ridings in Ontario are now potentially more competitive.
– **Correctness:** Needs verification (Political dynamics can shift; requires up-to-date analysis)
– **Importance:** Critical (Could directly affect the outcome of seat counts for the party)
– **Relevance:** True (Highly relevant, directly impacts seat predictions)
10. **Fact:** It is crucial to verify reports as the newsfeed may contain unverified claims and propaganda.
– **Correctness:** True (Critical approach to news is important)
– **Importance:** Important (Verification of information impacts accuracy of election predictions)
– **Relevance:** True (Relevant to the reliability of the overall analysis)
Each fact’s verification is necessarily dependent on the latest data and reliable reports, particularly pollster statistics and political analysis, which would require cross-referencing with current data sources.
Fact-checked summary:
In the context of the upcoming Canadian federal parliamentary election, party leaders are concentrating efforts in the Greater Toronto Area, a crucial battleground that may influence election outcomes significantly. Key election issues in Ontario, such as healthcare, affordable housing, and economic challenges, are expected to drive voter decision-making, impacting how well the Conservative Party performs. Additionally, it is important to approach election-related news with a critical perspective, ensuring information is verified to ensure accurate predictions, as unverified claims can affect the analysis of potential election results. These factors play a significant role in shaping the Conservative Party’s chances in the election.
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: 5)
Querying Mistral (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: 6)
Querying OpenAI (AI predicts: [“less than 172”: 0.25, “between 172 and 205”: 0.35, “between 206 and 240”: 0.25, “more than 240”: 0.15] – confidence: 6)
Question Type: Multiple Choice
Confidence: 6
# LLM responses: 3
Model value:
* less than 172: 45%
* between 172 and 205: 35%
* between 206 and 240: 15%
* more than 240: 5%
We queried Claude, Mistral, OpenAI. A summary of what the responding AIs considered is as follows:
The reasoning behind the predictions about the Conservative Party’s seat count in upcoming elections centers around historical performance, current polling data, and the strategic importance of regions like the Greater Toronto Area (GTA). Historically, the Conservative Party has garnered between 119 and 170 seats, with current polls suggesting a similar outcome, typically within the 120-170 range. The GTA, a critical battleground, typically leans Liberal, making it a challenging area for Conservatives to gain significant traction despite strategic efforts focused on key issues such as healthcare and housing. Predictions consider potential changes in public sentiment due to economic factors or scandals and the impact of vote splitting among progressive parties. However, uncertainties in voter turnout, polling accuracy, and shifting public opinion could significantly influence election results, adding complexity to the forecast.
Runtime for both questions on this page: 129 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).
