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%. [Jeremy’s note: Think I’m going to have to do some work on the bot to recalibrate it.]
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 (13 hours ago), there are concerns about how Trump’s proposed tariffs would impact dockworkers, as they would likely be among the first to face layoffs and job cuts in the event of a trade war due to their crucial position in the global economy.
In January 2025, a major crisis was averted when the International Longshoremen’s Association (ILA) and the United States Maritime Alliance (USMX) reached a tentative six-year contract agreement, preventing what would have been the second strike in four months. The deal covers approximately 45,000 dock workers. However, it’s worth noting that the agreement did not include terms on automation, which remains one of the most contentious issues between the parties.
The resolution came after significant tension, as workers had threatened to strike on January 15, 2025, which could have affected ports from Maine to Texas. The potential strike had raised concerns about inflation and supply chain disruptions. The successful negotiation helped prevent what experts warned could have led to higher prices and shortages of consumer goods.
The situation remains dynamic, particularly with the new concerns about how potential trade policies could affect the dock working industry despite the recent contract agreement.
Summarizing outside newsfeed:
“Recent reports highlight ongoing concerns about the impact of potential tariffs proposed by Trump on dockworkers, who might face layoffs due to their critical role in global trade. Earlier in 2025, a major strike was avoided through a tentative six-year contract agreement between the International Longshoremen’s Association (ILA) and the United States Maritime Alliance (USMX), covering about 45,000 workers, though contentious issues like automation remain unresolved. This resolution averted a strike that threatened ports from Maine to Texas and could have significantly disrupted supply chains and contributed to inflation. Despite this agreement, the situation remains fluid, as uncertainties about trade policies continue to pose challenges for the dockworking industry.”
Fact-checking news summary:
Here is a list of specific facts from the summary, along with their verification, importance, and relevance to the question:
1. **Fact:** Recent reports highlight ongoing concerns about the impact of potential tariffs proposed by Trump on dockworkers, who might face layoffs due to their critical role in global trade.
– **Verification (True/False):** True. Concerns about tariffs proposed by Trump affecting dockworkers are consistent with trade policies discussed during his administration, affecting industries involved in global trade.
– **Importance:** Lesser importance. While tariffs impact overall conditions, they do not directly address the automation discussion relevant to the negotiation table mentioned in the original question.
– **Relevance (True/False):** False. The details of tariffs and potential layoffs are not directly relevant to predicting a strike in Q1 2025 related to automation discussions.
2. **Fact:** Earlier in 2025, a major strike was avoided through a tentative six-year contract agreement between the International Longshoremen’s Association (ILA) and the United States Maritime Alliance (USMX).
– **Verification (True/False):** True. It is plausible based on the context given, suggesting recent events leading to an agreement to avoid a strike.
– **Importance:** Important. This agreement directly addresses the resolution of a major concern (avoiding a strike), which is highly relevant to the probability of a strike in Q1 2025.
– **Relevance (True/False):** True. The avoidance of a strike is relevant to assessing the likelihood of industrial action in Q1 2025.
3. **Fact:** This agreement covers about 45,000 workers.
– **Verification (True/False):** True. The number aligns with typical agreement scales in such negotiations.
– **Importance:** Lesser importance. The specific number of workers covered provides scope but doesn’t alter the strike probability analysis.
– **Relevance (True/False):** True. Knowing the number of workers covered indirectly affects the understanding of the scale of potential disruptions.
4. **Fact:** Contentious issues like automation remain unresolved.
– **Verification (True/False):** True. It follows logically that not all issues, like automation, would be resolved in a tentative agreement.
– **Importance:** Critical. Automation is directly related to future negotiations and potential causes of a strike.
– **Relevance (True/False):** True. Automation is a key issue influencing the probability of a strike.
5. **Fact:** This resolution averted a strike that threatened ports from Maine to Texas.
– **Verification (True/False):** True. Ports along the East Coast and Gulf are typical for dockworker negotiations and unionized actions.
– **Importance:** Important. The geographic scope underscores the significance of the agreement.
– **Relevance (True/False):** True. The scope ties directly to understanding the potential impact of a strike.
6. **Fact:** A strike could have significantly disrupted supply chains and contributed to inflation.
– **Verification (True/False):** True. Historical reports suggest strikes disrupt supply chains, affecting inflation.
– **Importance:** Important. Economic consequences amplify the significance of resolving labor disputes.
– **Relevance (True/False):** True. Understanding economic impacts helps weigh the pressure to avoid strikes.
7. **Fact:** The situation remains fluid due to uncertainties about trade policies, posing challenges for the dockworking industry.
– **Verification (True/False):** True. Global trade uncertainties consistently affect industries like dockworking.
– **Importance:** Important. The broader context of trade policies adds to uncertainties affecting labor stability.
– **Relevance (True/False):** True. These uncertainties contribute indirectly to assessing the probability of a strike, given their impact on negotiations.
These facts contribute to understanding the complexities and pressures surrounding dockworker negotiations and the potential for strike action in Q1 2025.
Fact-checked summary:
The recent avoidance of a major strike through a tentative six-year contract agreement between the International Longshoremen’s Association (ILA) and the United States Maritime Alliance (USMX) is highly relevant to the probability of a strike in Q1 2025, as it directly addresses a significant concern. This agreement, covering approximately 45,000 workers across ports from Maine to Texas, underscores the scope and importance of these negotiations. However, contentious issues like automation remain unresolved, which is critical because such issues are directly related to ongoing negotiations and potential causes of a strike. Additionally, a strike could have significant economic consequences by disrupting supply chains and contributing to inflation, amplifying the importance of resolving labor disputes. The situation is further complicated by global trade uncertainties that affect the dockworking industry, indirectly influencing the likelihood of a strike action in the first quarter of 2025.
OpenAI gives a base rate of 0.2 The following were considered in order to produce this base rate:
The base rate for labor strikes in industries with recent contract agreements is historically low, especially shortly after such agreements are reached. The tentative six-year contract, while it has unresolved issues, should decrease the immediate likelihood of a strike. However, the ongoing contentious issue of automation, combined with economic pressures and global trade uncertainties, raises the possibility but not to a high level due to the agreement already reached.
Some potential divergent considerations that might effect the base rate:
While the recent agreement should lower the chances of a strike, the unresolved issue of automation remains a sticking point. A potential escalation in economic or geopolitical circumstances affecting the industry or lack of progress on automation could increase the likelihood beyond the base rate. Also, changes in union leadership or external influences could impact the situation unexpectedly.
The following chain of events are necessary for the question to resolve positively:
– Breakdown in negotiations between the ILA and USMX over unresolved contentious issues, particularly automation. Likelihood: Relatively unlikely
– Failure to address or manage economic pressures impacting labor relations, exacerbating union dissatisfaction. Likelihood: Possible
– Absence of mitigating interventions from government or third-party mediators aimed at preventing a strike. Likelihood: Relatively unlikely
Querying Claude (AI predicts: 0.15 – confidence: 7)
Querying Mistral (AI predicts: 0.25 – confidence: 6)
Querying OpenAI (AI predicts: 0.25 – confidence: 6)
Question Type: Binary
Median from LLMs: 0.25
Base rate: 0.2 (from OpenAI)
SD: 0.05
Confidence: 6
Conf Mode: Normal
Mellers: 0.17
Reverse Mellers: 0.33
Theory of Mind: 0.35 (What did the LLMs think other LLMs predicted?)
Beta Distribution: 0.14
Close Type: A (B = cautious # closer to 50%; A/C = closer to extremes)
# LLM responses: 3
Model value: 0.25
We queried Claude, Mistral, OpenAI. A summary of what the responding AIs considered is as follows:
The AIs collectively suggest a low probability of a strike occurring in Q1 2025, primarily due to a newly agreed six-year contract between the International Longshoremen’s Association (ILA) and the United States Maritime Alliance (USMX), which typically reduces the likelihood of strikes shortly afterwards. Historical data supports a low base rate for strikes under similar conditions. However, unresolved issues regarding automation and ongoing economic pressures could present risks, potentially increasing the chance of a strike if they escalate. Moreover, while the time window for a potential strike within Q1 2025 is limited, any breakdown in automation negotiations or shifts in union leadership toward a more militant stance could alter current predictions and raise the strike probability. Additionally, external economic or geopolitical influences could exacerbate tensions, possibly leading to unexpected developments.
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?
* less than 172: 25%
* between 172 and 205: 40%
* between 206 and 240: 25%
* 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:
The Ontario provincial election campaign is currently at its midway point, with several notable developments:
1. Progressive Conservative (PC) leader Doug Ford’s party has seen a slip in recent polls amid mounting controversies, including a “hot mic” moment and restrictions on journalists’ questions. Ford is currently in Washington D.C. to address concerns about potential Trump-era tariffs, making him the only party leader campaigning outside the province.
2. Party leaders are preparing for their first debate scheduled for Friday in North Bay. The campaign has largely focused on issues like healthcare (particularly family doctors), Trump tariffs, and various regional concerns. The Progressive Conservatives, NDP, Liberals, and Greens have all been making campaign promises tracked by various media outlets.
At the federal level, there’s interesting movement in the polls:
– Donald Trump’s recent comments about potentially “taking over Canada” appear to be having an unexpected effect on Canadian politics, possibly helping Justin Trudeau’s Liberal Party rebound in popularity after months of low polling numbers.
– Conservative Leader Pierre Poilievre has responded by pledging to expand Canada’s military presence in the Arctic, aligning with some Trump administration positions while maintaining a stance of Canadian sovereignty.
All of this is occurring against a backdrop of increasing attention to younger voters, with reports indicating a notable trend of young people showing growing support for conservative positions in various regions of Canada.
Summarizing outside newsfeed:
“The Ontario provincial election is at its midpoint, with the Progressive Conservative (PC) party, led by Doug Ford, experiencing a dip in polls due to recent controversies, including a “hot mic” incident and restricted press interactions, as Ford addresses U.S. tariff issues in Washington, D.C. The first leaders’ debate is set for Friday in North Bay, with campaign themes centering on healthcare, tariffs, and regional issues. At the federal level, Donald Trump’s comments about “taking over Canada” have unpredictably boosted support for Prime Minister Justin Trudeau’s Liberal Party, while Conservative Leader Pierre Poilievre promises increased Arctic military presence, reflecting a complex political landscape. Additionally, there is a reported trend of rising conservative support among young Canadian voters. The information in this newsfeed should be regarded cautiously, as it may contain rumors or propaganda.”
Fact-checking news summary:
Here is a list of specific facts extracted from the summary, along with their evaluations:
1. **Fact:** The Ontario provincial election is at its midpoint.
– **Checking:** Assuming the date of the summary is current, this statement can be verified based on the specific election calendar in Ontario at the time.
– **Correctness:** True/False (depends on the specific timeframe information not given here).
– **Importance:** Unimportant to the resolution of the question about federal elections.
– **Relevance:** False; it does not pertain to the federal seat prediction.
2. **Fact:** The Progressive Conservative (PC) party, led by Doug Ford, is experiencing a dip in the polls.
– **Checking:** Difficult to confirm without recent polling data.
– **Correctness:** True/False (requires polling data from the time).
– **Importance:** Lesser importance to the federal election.
– **Relevance:** False; this is about provincial politics.
3. **Fact:** Doug Ford has faced controversies, including a “hot mic” incident and restricted press interactions.
– **Checking:** These can occur and get reported, but verification needs a contemporary news source.
– **Correctness:** True/False (depends on news reporting).
– **Importance:** Unimportant to the resolution of the federal election question.
– **Relevance:** False; primarily affects provincial and not federal dynamics.
4. **Fact:** Doug Ford is addressing U.S. tariff issues in Washington, D.C.
– **Checking:** Requires location-based confirmation, and relevance to federal prediction is indirect.
– **Correctness:** True/False (requires news confirmation).
– **Importance:** Unimportant; does not directly impact federal election predictions.
– **Relevance:** False; more relevant to provincial issues.
5. **Fact:** The first leaders’ debate is set for Friday in North Bay.
– **Checking:** Depends on confirmation of scheduling from credible sources.
– **Correctness:** True/False (requires event confirmation).
– **Importance:** Lesser importance; relates to internal provincial dynamics.
– **Relevance:** False; specific to Ontario’s election, not federal.
6. **Fact:** Campaign themes are centering on healthcare, tariffs, and regional issues.
– **Checking:** Typical themes but subjective without stated data presence.
– **Correctness:** True/False (depends on explicit election campaign information).
– **Importance:** Unimportant; no direct link to the federal seat prediction.
– **Relevance:** False; mainly relevant within Ontario’s elections.
7. **Fact:** Donald Trump’s comments about “taking over Canada” unpredictably boosted support for Justin Trudeau’s Liberal Party.
– **Checking:** Requires verification of comments and polling data trends after the comments.
– **Correctness:** True/False (depends on the existence of these comments and correlational data).
– **Importance:** Important; this affects federal level dynamics.
– **Relevance:** True; has potential relevance to federal electoral outcomes.
8. **Fact:** Conservative Leader Pierre Poilievre promises an increased Arctic military presence.
– **Checking:** Policy positions stated by party leaders are usually documented.
– **Correctness:** True/False (policy platform confirmation needed).
– **Importance:** Lesser importance; reflects possible defense policy not directly seating.
– **Relevance:** True; part of the federal party strategy though indirect to seat count.
9. **Fact:** There is a reported trend of rising conservative support among young Canadian voters.
– **Checking:** Requires polling and demographic trend analysis for verification.
– **Correctness:** True/False (depends on available polling data).
– **Importance:** Important; demographic shifts can influence federal elections.
– **Relevance:** True; impacts potential voter base influence in federal election.
10. **Fact:** The newsfeed information may contain rumors or propaganda.
– **Checking:** General statement, always prudent to verify all reports.
– **Correctness:** True; it’s a cautionary note rather than specific misinformation.
– **Importance:** Important; affects trustworthiness of information.
– **Relevance:** True; relevant to assessing the summary’s entire information validity.
Overall, the majority of the facts in the summary relate to provincial rather than federal politics, thus they hold minimal direct relevance to predicting the number of seats the Conservative Party might win in the next federal election.
Fact-checked summary:
Based on the fact-checked items relevant to predicting the number of seats the Conservative Party might win in Canada’s next federal parliamentary election, there are several key points to consider. A noteworthy boost for Justin Trudeau’s Liberal Party was reportedly unpredictable, stemming from comments made by Donald Trump about “taking over Canada.” This could potentially influence federal dynamics and, indirectly, the seat count. Furthermore, there is a reported trend of increasing conservative support among young Canadian voters, which is important due to its potential impact on the federal election through demographic changes. Lastly, information validity remains crucial; it’s important to verify news reports to ensure reliable assessments, underscoring the need for critical evaluation of sources when considering predictions about election outcomes.
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”: 0.2, “between 172 and 205”: 0.45, “between 206 and 240”: 0.25, “more than 240”: 0.1] – confidence: 6)
Querying OpenAI (AI predicts: [“less than 172”: 0.25, “between 172 and 205”: 0.3, “between 206 and 240”: 0.35, “more than 240”: 0.1] – confidence: 6)
Question Type: Multiple Choice
Confidence: 6
# LLM responses: 3
Model value:
* less than 172: 0.25
* between 172 and 205: 0.4
* between 206 and 240: 0.25
* more than 240: 0.1
We queried Claude, Mistral, OpenAI. A summary of what the responding AIs considered is as follows:
The AIs collectively analyze the Conservative Party’s potential performance in upcoming Canadian elections by considering historical data, recent polling trends, and the influence of current political dynamics. Notably, there is an increase in conservative support among young voters, which could lead to gains in seats, although attaining a majority government appears unlikely. Potential external influences, such as Donald Trump’s comments, introduce uncertainty as they may provoke a rally-around-the-flag effect benefiting the Liberals. The reliability of polling data is questioned due to past instances of significant shifts during campaigns, and the unpredictability of young voter turnout further complicates predictions. Thus, while the Conservatives may surpass historical seat counts, uncertainties regarding political events, voter behavior, and regional variations mean that unexpected outcomes remain possible.
Runtime for both questions total: 144 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).
