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, 25%, up from 15% yesterday.
[Carolyn says: Today our bot has reverted to contradicting itself by first pointing out that the deal to avert a strike is “tentative,” but further reporting as if it is a done deal by referring to “The resolution of this labor dispute.” On the plus side, its self-fact checking operation below clarifies that negotiations to prevent a strike are ongoing.]
Obtaining outside newsfeed. News from various sources. Based on the most recent news articles, here’s a summary of the US dockworkers situation:
The International Longshoremen’s Association (ILA), representing 45,000 dockworkers on the U.S. East and Gulf Coasts, has reached a tentative deal with port operators, averting a potential strike that was looming. This comes after negotiations resumed in early January 2024 following a brief three-day strike in October 2023. The key point of contention has been automation, with the ILA strongly opposing the expansion of semi-automated crane construction due to concerns about job security.
The previous strike was suspended until January 15, 2025, giving both parties time to negotiate a new contract. The stakes were high, as a prolonged strike could have significant economic implications, potentially leading to supply chain disruptions, delivery delays, and higher consumer prices. The agreement is particularly important for maintaining smooth operations at major ports along the Atlantic and Gulf coasts.
The resolution of this labor dispute represents a critical development for the U.S. supply chain infrastructure, as any disruption to port operations could have ripple effects throughout the economy. The agreement helps avoid potential inflation and shortages that experts warned could result from a strike, while also addressing the union’s concerns about job security in the face of increasing automation in port operations.
Summarizing outside newsfeed:
“The International Longshoremen’s Association (ILA) and port operators have reached a tentative agreement, averting a potential strike by 45,000 dockworkers on the U.S. East and Gulf Coasts. This follows resumed negotiations in January 2024 after a brief strike in October 2023, primarily over concerns about job security related to automation. The agreement delays further strikes until January 15, 2025, allowing more time for contract discussions and aiming to prevent economic impacts, such as supply chain disruptions and inflation. The resolution is significant for maintaining smooth operations at key ports and addressing the union’s automation concerns.”
Fact-checking news summary:
### List of Specific Facts from the Summary:
1. **Fact 1:** The International Longshoremen’s Association (ILA) and port operators have reached a tentative agreement.
– **Truth:** True. The summary indicates this is the case, and external context corroborates the tentative nature of such agreements in labor disputes.
– **Importance for Resolution:** Important. The tentative agreement impacts the likelihood of a strike.
– **Relevance to Outcome:** True. It directly affects the probability of a strike in Q1 2025.
2. **Fact 2:** The agreement averts a potential strike by 45,000 dockworkers on the U.S. East and Gulf Coasts.
– **Truth:** True. The summary clearly states this outcome directly follows the agreement.
– **Importance for Resolution:** Critical. Preventing a strike is crucial to assessing future strike probabilities.
– **Relevance to Outcome:** True. Avoiding a strike is highly relevant to predicting future actions.
3. **Fact 3:** Negotiations resumed in January 2024 after a brief strike in October 2023.
– **Truth:** True. The summary provides an internally consistent timeline, and strike occurrences lead to resumed negotiations.
– **Importance for Resolution:** Important. Understanding past negotiation patterns helps forecast future negotiations.
– **Relevance to Outcome:** True. History of negotiations and strikes contributes to the future probability assessment.
4. **Fact 4:** The October 2023 strike was primarily over concerns about job security related to automation.
– **Truth:** True. The summary is internally consistent regarding the issues leading to the strike.
– **Importance for Resolution:** Important. The causes of past strikes inform ongoing negotiation points.
– **Relevance to Outcome:** True. Automation concerns are a core issue influencing future bargaining and strike probability.
5. **Fact 5:** The agreement delays further strikes until January 15, 2025.
– **Truth:** True. The summary indicates a delay in strikes until a specific date.
– **Importance for Resolution:** Critical. The agreement’s timeline directly relates to the question of strikes in Q1 2025.
– **Relevance to Outcome:** True. A delay is one of the most relevant pieces of information for predicting strikes in early 2025.
6. **Fact 6:** The purpose of the delay is to allow more time for contract discussions and prevent economic impacts like supply chain disruptions and inflation.
– **Truth:** True. The summary’s rationale is both internally consistent and aligns with typical objectives in labor agreements.
– **Importance for Resolution:** Important. Understanding objectives provides context but doesn’t directly predict outcomes.
– **Relevance to Outcome:** True. Economic impact prevention is relevant and affects stakeholders’ future actions.
7. **Fact 7:** The resolution is significant for maintaining smooth operations at key ports and addressing the union’s automation concerns.
– **Truth:** True. The resolution of labor disputes is significant for operations and issues raised.
– **Importance for Resolution:** Important. Significance indicates stakeholder priorities and negotiation outcomes.
– **Relevance to Outcome:** True. Smooth operations and resolved concerns directly influence strike probability.
### Evaluation of Resolution Probability
– The tentative agreement and delayed strike indicate reduced probability of a strike in Q1 2025, given ongoing negotiations and past resolutions. All facts presented contribute significantly to understanding this probability metric within the specified timeline.
Fact-checked summary:
A tentative agreement has been reached between the International Longshoremen’s Association (ILA) and port operators, which is crucial to the likelihood of a strike, as it directly impacts the probability of such an event in Q1 2025. The agreement averts a potential strike by 45,000 dockworkers on the U.S. East and Gulf Coasts, making it critical in assessing future strike probabilities. Negotiations resumed in January 2024 after a brief strike in October 2023. This reflects the ongoing pattern where past negotiations influence future discussions, especially since the October 2023 strike was primarily over job security issues related to automation. The agreement includes a delay in further strikes until January 15, 2025, making this timeline essential to predicting any strikes in early 2025. This delay allows more time for contract discussions and aims to prevent economic impacts, such as supply chain disruptions and inflation, which is an important context for understanding the objectives behind the agreement. Lastly, the resolution is significant for maintaining smooth operations at key ports and addressing the union’s automation concerns, directly influencing the probability of a strike. Therefore, the probability of a strike in Q1 2025 is reduced given the tentative agreement and the focus on ongoing negotiations.
OpenAI gives a base rate of 0.15. The following were considered in order to produce this base rate:
The base rate is derived from historical data on the frequency of strikes following tentative agreements and the pattern of union negotiations in the shipping industry. Given the recent tentative agreement and plans to delay further strikes until January 15, 2025, the probability of a strike in Q1 2025 is reduced. Considering the importance of maintaining operations and the focus on negotiations, the chance of a strike occurring is lower than average under these conditions.
Some potential divergent considerations that might effect the base rate:
If the agreement is not ratified or if critical union concerns, especially regarding automation, are not effectively addressed, the risk of a strike increases. Additionally, unexpected economic disruptions or changes in political dynamics could alter the situation, leading to a higher likelihood of a strike. These factors could significantly impact the base rate and necessitate an adjustment in probability estimation.
The following chain of events are necessary for the question to resolve positively:
– The tentative agreement between the ILA and port operators fails to be ratified or implemented. Unlikely
– Further negotiations scheduled before January 15, 2025, breakdown or do not address key concerns satisfactorily. Unlikely
– Major unresolved issues, such as job security related to automation, lead to renewed tensions and a strike call by the union. Possible
– Economic or political factors exacerbate union grievances, leading to increased strike motivation. Possible
Querying Claude (AI predicts: 0.35 – confidence: 6)
Querying Mistral (AI predicts: 0.2 – confidence: 6)
Querying OpenAI (AI predicts: 0.25 – confidence: 6)
Question Type: Binary
Median from LLMs: 0.25
Base rate: 0.15 (from OpenAI)
SD: 0.06
Confidence: 6
Conf Mode: Normal
Mellers: 0.17
Reverse Mellers: 0.33
Theory of Mind: 0.4 (What did the LLMs think other LLMs predicted?)
Beta Distribution: 0.06
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:
Several factors influence the prediction regarding the likelihood of a strike in Q1 2025. The recent tentative agreement between the ILA and port operators reduces this likelihood, as historically strikes are less frequent following such agreements. This compromise, along with the scheduled return to bargaining on January 15, 2025, indicates structured negotiations. However, unresolved issues about automation and job security remain contentious and could increase the risk of a strike if not settled. Economic or political factors could also heighten tensions. Conversely, successful salary negotiations might have created goodwill, and both parties may be incentivized to avoid economic disruptions given recent challenges, potentially reducing the probability of a strike further. Overall, while the probability is somewhat reduced, unresolved automation issues and external pressures still pose risks..
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: 35%
* between 206 and 240: 35%
* more than 240: 15%
Most Recent Developments (1-2 days ago):
– Ontario Premier Doug Ford has called a snap election, primarily focused on fighting potential tariffs threatened by Donald Trump. Ford positions himself as the best economic steward to handle these challenges. Opposition parties are focusing their campaigns on healthcare issues.
– Elections BC has suspended its investigation into Conservative claims of vote violations due to an ongoing court case where a party candidate named the chief electoral officer in a court filing.
– Green Party leadership is pushing for Parliament to adopt foreign interference protection measures before the next federal election.
Broader Context (Past Week):
– Recent Angus Reid polling suggests the federal Liberals would perform better with Mark Carney as leader, though Conservative Pierre Poilievre is still favored to win the next federal election. Key election issues identified include cost of living, housing, healthcare, economy, and climate change.
– The Conservative Party, led by Poilievre, is showing strong polling numbers ahead of the next federal election, which must be held by October 20 but may occur sooner. Equity investors are reportedly optimistic about a potential Conservative victory, anticipating it could lead to increased market returns and a shift in economic priorities after nine years of Liberal government.
This news cycle shows significant political activity at both provincial (particularly Ontario) and federal levels, with economic issues, foreign interference concerns, and leadership dynamics playing major roles in the electoral landscape.
Summarizing outside newsfeed:
“Recent developments in Canada’s political landscape include Ontario Premier Doug Ford calling a snap election to address potential tariffs from Donald Trump, positioning himself as the economic candidate, while opposition parties focus on healthcare issues. In British Columbia, Elections BC has paused its investigation into Conservative vote violation claims due to an ongoing court case. The Green Party is advocating for foreign interference protection measures before the next federal election. Federally, polling indicates that although Mark Carney could bolster the federal Liberals’ chances, Pierre Poilievre’s Conservatives remain favored to win, with key issues including the economy and climate change taking center stage. Economic optimism among investors also grows in anticipation of a potential Conservative victory, reflecting a possible shift from nine years of Liberal governance.”
Fact-checking news summary:
Here is a list of specific facts from the summary, followed by an analysis of their consistency, importance, and relevance to the question about the number of seats the Conservative Party will win in Canada’s next federal parliamentary election.
1. **Ontario Premier Doug Ford called a snap election to address potential tariffs from Donald Trump.**
– **Correctness:** False. Canadian provincial premiers do not call federal elections. Donald Trump does not have direct jurisdiction over Canada to impose tariffs that require immediate provincial election response.
– **Importance:** Unimportant to critical. While the method is incorrect, any influence of international economic policies on elections can be critical.
– **Relevance:** False. This does not directly relate to the number of seats the federal Conservative Party might win.
2. **Opposition parties focus on healthcare issues.**
– **Correctness:** Potentially true. While plausible, this fact lacks specificity to validate without more data.
– **Importance:** Important. Healthcare is a significant election issue that could impact voter behavior.
– **Relevance:** True. Healthcare policies can influence the number of seats won.
3. **Elections BC has paused its investigation into Conservative vote violation claims due to an ongoing court case.**
– **Correctness:** Impossible to verify without specific details. Requires data about current Elections BC activities.
– **Importance:** Important. Vote violations can affect public perception and electoral outcomes.
– **Relevance:** True. The outcome of such investigations could influence the number of seats won.
4. **The Green Party is advocating for foreign interference protection measures before the next federal election.**
– **Correctness:** Potentially true. Parties have expressed concern about foreign interference in elections globally, including Canada.
– **Importance:** Important. Ensuring fair elections is crucial for democratic processes.
– **Relevance:** True. Could potentially impact election integrity and results.
5. **Polling indicates that Mark Carney could bolster the federal Liberals’ chances, but Pierre Poilievre’s Conservatives remain favored to win.**
– **Correctness:** Potentially true. Polls fluctuate but indicate trends regarding party leadership influence.
– **Importance:** Critical. Polling data directly informs predictions about election outcomes.
– **Relevance:** True. Provides a direct indication of potential Conservative success.
6. **Key issues include the economy and climate change.**
– **Correctness:** True. These issues are often central in political discourse.
– **Importance:** Important. Economic and climate policies significantly influence voter preferences.
– **Relevance:** True. These issues are relevant to vote outcomes and seat distribution.
7. **Economic optimism among investors grows in anticipation of a potential Conservative victory.**
– **Correctness:** Potentially true. Economic outlooks often reflect perceived political shifts.
– **Importance:** Important. Investor sentiment can reflect broader economic expectations that affect voter decisions.
– **Relevance:** True. Sets the backdrop for economic narratives influencing election results.
8. **Reflecting a possible shift from nine years of Liberal governance.**
– **Correctness:** True. The Liberal Party has been in power federally since 2015.
– **Importance:** Important. Historical context of party governance affects voter fatigue and election dynamics.
– **Relevance:** True. Understanding past governance influences future electoral results.
Overall, the facts that directly address political trends, polling data, and key issues are most pertinent to assessing the Conservative Party’s potential success in the election. Less directly relevant facts, like the purported snap election in Ontario, do not informative about federal seat outcomes.
Fact-checked summary:
In anticipation of Canada’s next federal parliamentary election, several true and relevant facts suggest factors that could influence the outcome. Historically, the Liberal Party has been in power since 2015, which is significant as extended governance can lead to voter fatigue and shifts in political preference, potentially benefiting the Conservatives. Key issues such as the economy and climate change play a crucial role in shaping voter preferences and thus are highly relevant to the election results and seat distribution. Polling data suggests that even though Mark Carney could bolster the Liberals, Pierre Poilievre’s Conservatives remain favored, underscoring their potential success. Additionally, economic optimism among investors in a potential Conservative victory reflects broader expectations that might sway voter decisions. These facts together create a context of possible change, emphasizing political trends that could influence the number of seats the Conservative Party may win.
Querying Claude (AI predicts: [“less than 172”: 0.2, “between 172 and 205”: 0.45, “between 206 and 240”: 0.3, “more than 240”: 0.05] – confidence: 5)
Querying Mistral (AI predicts: [“less than 172”: 0.1, “between 172 and 205”: 0.35, “between 206 and 240”: 0.35, “more than 240”: 0.2] – confidence: 7)
Querying OpenAI (AI predicts: [“less than 172”: 0.15, “between 172 and 205”: 0.3, “between 206 and 240”: 0.4, “more than 240”: 0.15] – confidence: 6)
Question Type: Multiple Choice
Confidence: 6
# LLM responses: 3
Model value:
* less than 172: 0.15
* between 172 and 205: 0.35
* between 206 and 240: 0.35
* more than 240: 0.15
We queried Claude, Mistral, OpenAI. A summary of what the responding AIs considered is as follows:
The predictions regarding the Conservative Party’s prospects in the election are influenced by several factors. Key considerations include potential voter fatigue with the Liberal Party, which has been in power since 2015, along with strong current polling support for Pierre Poilievre’s Conservatives. Economic concerns, historically beneficial for the Conservatives, also play a role in this forecast. However, the predictions are tempered by uncertainties such as the volatility of polling data, potential shifts in public opinion on key issues like climate change, and regional dynamics in provinces such as Quebec and Ontario. Furthermore, the potential influence of political figures such as Mark Carney and unforeseen events could significantly impact the election outcome, emphasizing the need for caution in projecting significant shifts in the political landscape.
Runtime for both questiobsn on this page: 140 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).