Updates from BestWorld’s AI Botmaster Jeremy Lichtman of Feb. 10, 2025

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, 29%. [Jeremy’s note: The 29% on dock-workers is statistical noise. That is to say,  the prompting discourages the individual LLMs from going near zero, and we’re taking a median of their values. It’s basically a zero.]

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 Developments:
A potential second major port strike was averted in January 2025 when the International Longshoremen’s Association (ILA), representing 45,000 dock workers on the U.S. East and Gulf Coasts, reached a tentative agreement with the United States Maritime Alliance (USMX) employer group. The deal resulted in a new six-year contract, preventing what could have been a significant disruption to the U.S. supply chain. [Carolyn’s note: false because the deal is “tentative.” More negotiations are required to ensure that the deal will be adopted.] Key Details:
– The agreement came just before a January 15 deadline that could have triggered another strike
– While most issues were resolved, the agreement notably did not include final terms on automation, which remains one of the most contentious issues between the parties
– The previous strike threat had impacted shipping patterns, with container expert John McCown noting that imports at East and Gulf Coast ports were 3.9% below pandemic-era averages during this period
Impact and Implications:
The resolution of this potential strike was particularly important as it helped prevent what experts warned could have led to increased inflation and supply shortages. The agreement was seen as crucial for maintaining stability in U.S. ports, which are vital for both domestic and international trade. The agricultural sector was particularly concerned about the potential impact on exports of U.S. meat products and other perishable goods that rely on refrigerated containers.

Summarizing outside newsfeed:
“In January 2025, a major port strike was narrowly avoided when the International Longshoremen’s Association and the United States Maritime Alliance reached a tentative six-year contract agreement, averting a significant disruption to the U.S. supply chain. The deal was struck just before a critical January 15 deadline, although it left unresolved the contentious issue of automation. Previously, the threat of a strike had already affected shipping patterns, with East and Gulf Coast port imports dropping 3.9% below pandemic-era averages. The agreement was seen as crucial in preventing potential inflation and supply shortages, with the agricultural sector particularly concerned about export impacts on U.S. meat products and other perishable goods. The situation highlights ongoing tensions in labor negotiations, particularly concerning automation, and underscores the importance of stable operations at U.S. ports for both domestic and international trade.”

Fact-checking news summary:
Below is a list of specific facts from the summary, along with an analysis of their accuracy, importance to the resolution of the question, and relevance to the outcome of assessing the probability of a strike in Q1 2025.

1. **Fact**: In January 2025, a major port strike was narrowly avoided when the International Longshoremen’s Association (ILA) and the United States Maritime Alliance (USMX) reached a tentative six-year contract agreement.
– **Check**: True. The information appears consistent and plausible based on standard labor negotiation processes.
– **Importance**: Important. This agreement directly impacts the likelihood of a strike.
– **Relevance**: True. A reached agreement significantly reduces the probability of a Q1 2025 strike.

2. **Fact**: The deal was struck just before a critical January 15 deadline.
– **Check**: True. This is internally consistent with the original question mentioning the bargaining table on January 15.
– **Importance**: Critical. The timing of the agreement is crucial in evaluating the immediate risk of a strike.
– **Relevance**: True. Meeting the deadline indicates a reduced strike risk in Q1 2025.

3. **Fact**: The contentious issue of automation was left unresolved in the agreement.
– **Check**: True. This is plausible as automation is commonly a contentious topic in labor negotiations.
– **Importance**: Important. Unresolved major issues can exacerbate future labor tensions.
– **Relevance**: True. Continuing disputes over automation could impact future strike probabilities.

4. **Fact**: The threat of a strike had already affected shipping patterns, with East and Gulf Coast port imports dropping 3.9% below pandemic-era averages.
– **Check**: True (assuming specific data corroborates the 3.9% figure). The impact on shipping patterns is a plausible effect of a strike threat.
– **Importance**: Lesser importance. It provides context but doesn’t directly influence the probability of a strike occurring in Q1 2025.
– **Relevance**: True. Indicates broader economic impacts of labor tensions.

5. **Fact**: The agreement was seen as crucial in preventing potential inflation and supply shortages.
– **Check**: True. This is consistent with economic principles; disruptions can lead to supply chain issues.
– **Importance**: Important. It reflects the high stakes involved in these negotiations.
– **Relevance**: True. Highlights economic reasons to avoid strikes.

6. **Fact**: The agricultural sector was particularly concerned about export impacts on U.S. meat products and other perishable goods.
– **Check**: True. Agricultural supply chains are especially vulnerable to port disruptions.
– **Importance**: Lesser importance. Sector-specific impacts are secondary to the broader question of a strike.
– **Relevance**: True. Provides context for why averting a strike was prioritized.

7. **Fact**: The situation highlights ongoing tensions in labor negotiations, particularly concerning automation.
– **Check**: True. Automation is a persistent issue in labor discussions.
– **Importance**: Important. Continued tensions could influence future bargaining and strike risks.
– **Relevance**: True. Indicates the potential for future conflicts that could lead to strikes.

8. **Fact**: Stable operations at U.S. ports are important for both domestic and international trade.
– **Check**: True. Ports play crucial roles in trade.
– **Importance**: Important. Economic stability reinforces the drive to avoid strikes.
– **Relevance**: True. Underlines the broader impact port stability has on the economy.

Overall, the summary provides a picture of reduced immediate strike risk due to the agreement but highlights the unresolved issue of automation that could influence future developments.

Fact-checked summary:
In January 2025, a major strike at U.S. ports was narrowly averted when a tentative six-year contract agreement was reached between the International Longshoremen’s Association (ILA) and the United States Maritime Alliance (USMX) just before a critical January 15 deadline. This agreement significantly reduces the probability of a strike in Q1 2025, as it directly impacts labor relations and meets crucial timing deadlines that would exacerbate tensions. However, the contentious issue of automation was left unresolved, which could impact future strike probabilities as it remains a significant source of labor tension. While the threat of a strike had already affected shipping patterns, reducing East and Gulf Coast port imports, the agreement was seen as crucial in preventing potential inflation and supply shortages, illustrating the high stakes involved. Stable operations at U.S. ports remain vital for both domestic and international trade, reinforcing the importance of avoiding strikes. The ongoing tension regarding automation remains a potential influence on future bargaining dynamics.

OpenAI gives a base rate of 0.8. The following were considered in order to produce this base rate:

To arrive at the base rate, I considered the recent completion of the tentative six-year contract agreement, which significantly reduces the likelihood of a strike in the immediate future by establishing clear terms between the ILA and USMX. Historically, such agreements tend to stabilize labor relations for several years, especially when significant concessions or compromises, like meeting critical deadlines, are involved. However, the unresolved issue of automation introduces an element of uncertainty. Reviewing past port strike frequencies, such agreements tend to result in high stability, thus assigning an 80% (or ‘Probable’) likelihood that there will be no strike in Q1 2025.

Some potential divergent considerations that might affect the base rate: The primary divergent consideration is the unresolved issue of automation, which could prompt future discord and potential strikes if not addressed adequately or if new technology proposals exacerbate tensions. Additionally, any major external economic or geopolitical disruptions affecting trade could impact labor relations adversely, regardless of the contract’s current terms. Tensions regarding automation could gain momentum, altering the probability of peace despite the contract. Furthermore, economic downturns could diminish shipping volumes, affecting the perceived benefit of the contract terms.

The following chain of events are necessary to avoid a Q1 strike:
– No breakdown in communication between the ILA and USMX (Likely).
– Resolution of the automation issue or at least a temporary compromise (Uncertain).
 – Continued stable economic conditions to support the current labor agreement (Probable).
– Absence of major external shocks affecting U.S. ports, such as severe weather or geopolitical tensions (Highly Likely).

Querying Claude (AI predicts: 0.15 – confidence: 7)
Querying Mistral (AI predicts: 0.3 – confidence: 6)
Querying OpenAI (AI predicts: 0.2 – confidence: 6)
Question Type: Binary
Median from LLMs: 0.2
Base rate: 0.8 (from OpenAI)
SD: 0.06
Confidence: 6
Conf Mode: Low
Mellers: 0.12
Reverse Mellers: 0.29
Theory of Mind: 0.5 (What did the LLMs think other LLMs predicted?)
Beta Distribution: 1
Close Type: C (B = cautious # closer to 50%; A/C = closer to extremes)
# LLM responses: 3

Model value): 0.29 We queried Claude, Mistral, OpenAI. A summary of what the responding AIs considered is as follows: The recent tentative six-year contract agreement between the ILA and USMX, which includes provisions for salary increases, has markedly decreased the likelihood of a strike in Q1 2025 by providing stability in labor relations. Historically, such agreements have limited strike actions shortly after their enactment. However, the unresolved issue of automation still presents a significant source of tension, as it continues to be a contentious topic in negotiations. While the economic and geopolitical environment remains stable, the automation topic introduces an element of uncertainty, as it could prompt unexpected disputes or leverage for negotiations. Additionally, unforeseen external shocks or economic pressures could destabilize current conditions, increasing the risk of a strike despite the recent agreement. Overall, while the present risks suggest a low probability of immediate strikes, automation and unpredictable factors maintain a degree of uncertainty.





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: 37%
* between 172 and 205: 42%
* between 206 and 240: 16%
* more than 240: 6%

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:
– There’s a growing trend of young voters supporting the Conservative Party, particularly in regions like Newfoundland and Labrador, where both provincial and federal elections are upcoming this year.
– In Ontario’s election campaign, recent Nanos surveys show Premier Doug Ford’s Progressive Conservative lead over the Liberals has slightly shrunk. Both parties aired competing campaign ads during the Super Bowl.
– The Conservative Party has demonstrated significant fundraising strength, nearly doubling the combined totals of the Liberal and NDP parties in 2024.
Key Campaign Themes and Issues:
– The Conservative Party is planning a major campaign rebranding with a “Canada First rally” scheduled for February 15, where attendees are encouraged to wear red and white.
– Donald Trump’s potential influence is being viewed as an “X factor” in Canadian politics, particularly regarding trade relations and tariff threats.
– In Ontario specifically, major campaign issues include Ford’s controversial $60 billion tunnel transit proposal and healthcare concerns.

The political landscape shows the Conservative Party gaining momentum through strong fundraising and youth support, while traditional Liberal strongholds face new challenges. The upcoming elections at both provincial and federal levels are being shaped by domestic issues like healthcare and infrastructure, as well as international factors like U.S. relations under a possible second Trump presidency.

Summarizing outside newsfeed:
“Recent developments in Canadian politics suggest a shifting landscape, with the Conservative Party gaining traction among young voters and showcasing strong fundraising capabilities, surpassing the combined efforts of the Liberal and NDP parties. In Newfoundland and Labrador, both provincial and federal elections are on the horizon, while in Ontario, Doug Ford’s Progressive Conservatives face a diminishing lead over the Liberals, with both sides actively campaigning. Key issues include Ford’s costly transit proposal and ongoing healthcare debates, amidst concerns about the potential impact of Donald Trump’s influence on Canadian-U.S. relations. As the political arena evolves, traditional Liberal bastions encounter new challenges, and the Conservative Party prepares for a significant campaign event, underscoring a “Canada First” theme.”

Fact-checking news summary:
### List of Specific Facts Stated:

1. **The Conservative Party is gaining traction among young voters.**
– **Verification**: This statement implies a trend but does not provide specific data. It’s a general assessment and would require polling data for verification.
– **True/False**: Not verifiable with the information provided. Needs more data to confirm.
– **Importance to Resolution**: Important – If true, could influence the number of seats won.
– **Relevance to Outcome**: True – A shift in voter demographics is relevant to election outcomes.

2. **The Conservative Party has strong fundraising capabilities, surpassing the combined efforts of the Liberal and NDP parties.**
– **Verification**: Recent financial reports would need to be checked to verify this claim.
– **True/False**: Needs verification – subject to change over time and requires up-to-date financial data.
– **Importance to Resolution**: Important – Fundraising can significantly affect campaign effectiveness.
– **Relevance to Outcome**: True – Strong fundraising impacts election campaigns and potentially results.

3. **Provincial and federal elections are on the horizon in Newfoundland and Labrador.**
– **Verification**: This fact can be verified with a check on the election schedules.
– **True/False**: True – Depending on actual election cycles, but generally factual.
– **Importance to Resolution**: Lesser importance – These elections are geographically limited.
– **Relevance to Outcome**: True – Affects local outcomes, influences overall political climate.

4. **In Ontario, Doug Ford’s Progressive Conservatives face a diminishing lead over the Liberals.**
– **Verification**: Requires polling data from Ontario to confirm.
– **True/False**: Needs verification – Polls can confirm or deny current standings.
– **Importance to Resolution**: Important – Ontario is a key battleground in Canadian elections.
– **Relevance to Outcome**: True – Ontario’s political dynamics are critical to federal results.

5. **Key issues include Ford’s costly transit proposal and ongoing healthcare debates.**
– **Verification**: These issues can be confirmed through news reports and government statements.
– **True/False**: True – Frequently cited issues in Ontario politics.
– **Importance to Resolution**: Lesser importance – Specific issues may not directly impact federal Conservative seat count.
– **Relevance to Outcome**: True – Local issues can influence voter sentiment federally.

6. **Concerns exist about the potential impact of Donald Trump’s influence on Canadian-U.S. relations.**
– **Verification**: A subjective concern rather than a factual statement.
– **True/False**: True (in terms of being a concern) – but the impact’s reality would require further political analysis.
– **Importance to Resolution**: Unimportant – Not directly related to the Conservative seat count.
– **Relevance to Outcome**: False – Peripheral to predicting the Conservative Party’s seat total.

7. **Traditional Liberal bastions encounter new challenges.**
– **Verification**: Requires analysis of electoral trends and polls.
– **True/False**: Partially true – Shift in political dynamics is often talked about, but specific data is needed.
– **Importance to Resolution**: Important – A shift in these regions could increase Conservative seats.
– **Relevance to Outcome**: True – Directly pertains to potential changes in Conservative seat totals.

8. **The Conservative Party is preparing for a significant campaign event, underscoring a “Canada First” theme.**
– **Verification**: Can be confirmed through party announcements and event schedules.
– **True/False**: True – If scheduled and publicized.
– **Importance to Resolution**: Lesser importance – A single event’s impact can vary.
– **Relevance to Outcome**: False – A campaign theme alone does not determine seat count.

Overall, while several facts are indeed relevant and important to understanding the potential outcomes in Canadian politics, some require cautious validation and are of varying impact on the specific question about the Conservative Party’s potential seat count.

Fact-checked summary:
To determine how many seats the Conservative Party might win in Canada’s next federal parliamentary election, several confirmed facts are relevant. Provincial and federal elections are scheduled soon in Newfoundland and Labrador, which, while limited geographically, could influence the wider political landscape. In Ontario, an important battleground for Canadian elections, Doug Ford’s Progressive Conservatives face a diminishing lead over the Liberals, reflecting possible shifts in voter sentiment. Key issues in Ontario, such as Ford’s costly transit proposal and ongoing healthcare debates, are true concerns impacting local politics and hold potential sway over federal voter decisions. Additionally, traditional Liberal strongholds are encountering new political challenges, potentially increasing Conservative seat numbers if these changes result in Conservative gains. Each of these elements provides context but does not conclusively predict the specific number of seats the Conservatives will secure.

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

Model value:
* less than 172: 37%
* between 172 and 205: 42%
* between 206 and 240: 16%
* more than 240: 6%

We queried Claude, Mistral, OpenAI. A summary of what the responding AIs considered is as follows:
The various AI analyses suggest that predicting a dramatic increase in seats for the Conservative Party in Canada is unlikely due to several factors. Historical voting patterns and current provincial dynamics, particularly in Ontario, indicate only moderate gains for Conservatives, as support for provincial counterparts shows signs of weakening. While opportunities exist for gains in traditional Liberal strongholds facing challenges, these typically lead to incremental rather than drastic changes in seat counts. Furthermore, unpredictable shifts in voter sentiment and potential external events such as scandals or economic issues could alter the political landscape, complicating accurate forecasts. Consequently, while Conservatives may achieve moderate increases, surpassing significant seat thresholds seems improbable under the present circumstances.

Runtime: 152 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