Updates from BestWorld’s AI Botmaster Jeremy Lichtman of Feb. 11, 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, 15%. [Jeremy’s note: … 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:

In January 2025, a major potential strike was averted when the International Longshoremen’s Association (ILA), representing about 45,000 dockworkers at East and Gulf Coast ports, reached a tentative agreement with port employers. The union had previously conducted a three-day strike, but the new deal suspends any strike action until January 15, 2025, while negotiations continue for a new contract.

The most recent development, highlighted in a Cavalier Daily article from just 4 days ago, discusses the ongoing challenge of automation facing dockworkers’ unions. The article suggests that rather than opposing automation outright, unions should work with legislators to address the technological changes affecting the industry.
This agreement came after a tense period in late 2024, which included the union’s first strike in nearly 50 years in October. The key issues in the negotiations included demands for higher wages and protections against automation. The resolution of this dispute was significant as it prevented what could have been a highly disruptive strike at major U.S. ports.

Summarizing outside newsfeed:
“In January 2025, a potential strike by the International Longshoremen’s Association (ILA) was averted after a tentative agreement was reached with port employers, temporarily suspending any strike action while contract negotiations continue. This agreement followed a tense period in late 2024, including the union’s first strike in nearly 50 years, which centered on demands for higher wages and protections against automation. Additionally, a recent article from the Cavalier Daily emphasized the ongoing challenge of automation, proposing that unions collaborate with legislators to address these technological changes rather than opposing them outright. The resolution was crucial as it prevented a potentially disruptive strike at major U.S. ports.”

Fact-checking news summary:
Below is a list of specific facts extracted from the summary, along with an analysis of their correctness, importance, and relevance:

1. **Fact**: In January 2025, a potential strike by the International Longshoremen’s Association (ILA) was averted after a tentative agreement was reached with port employers, temporarily suspending any strike action while contract negotiations continue.
– **Checking**: True (assuming reliable data source).
– **Importance**: Critical, as it directly relates to the probability of a strike in Q1 2025.
– **Relevance**: True, since it affects the likelihood of a future strike.

2. **Fact**: The tentative agreement temporarily suspends any strike action while contract negotiations continue.
– **Checking**: True (based on the information provided).
– **Importance**: Important, as it specifically addresses the current state of negotiations and their impact on strike actions.
– **Relevance**: True, since it provides details on the status of the strike threat.

3. **Fact**: This agreement followed a tense period in late 2024, including the union’s first strike in nearly 50 years, centered on demands for higher wages and protections against automation.
– **Checking**: Potentially False, as the text does not provide corroborative evidence of a strike actually occurring in late 2024. Verification needed.
– **Importance**: Important, as the occurrence of a recent strike would influence the likelihood of future strikes.
– **Relevance**: True, as recent strike history is pertinent to assessing strike probability.

4. **Fact**: A recent article from the Cavalier Daily emphasized the ongoing challenge of automation, proposing that unions collaborate with legislators to address technological changes.
– **Checking**: The publication of an article needs verification for accuracy.
– **Importance**: Lesser importance, as it’s more background context on the broader issue rather than the immediate negotiation scenario.
– **Relevance**: True, since attitudes towards automation affect union strategies and negotiations.

5. **Fact**: The resolution prevented a potentially disruptive strike at major U.S. ports.
– **Checking**: True (assuming satisfactory completion of agreements as described).
– **Importance**: Important, as the prevention of a strike directly impacts economic stability and trends.
– **Relevance**: True, as the prevention affects the probability of future disruptions.

Summary: The narrative of ongoing negotiations and averted strikes are critical to assessing the probability of a strike in Q1 2025. However, the historical context of previous strikes, particularly the claim regarding a strike in late 2024, should be examined further for accuracy. Generally, automation is a significant concern but is a broader issue influencing longer-term strategies, rather than the immediate strike risk of Q1 2025.

Fact-checked summary:
In January 2025, a potential strike by the International Longshoremen’s Association was averted after a tentative agreement with port employers was reached, temporarily suspending any strike actions while contract negotiations continue. This outcome is critical as it directly relates to the probability of a strike in Q1 2025, reducing immediate threats of disruption. The tentative agreement specifically addresses the current negotiations’ impact, providing assurance that the risk of a strike has been suspended for now. The resolution prevented a potentially disruptive strike at major U.S. ports, which is important for maintaining economic stability and underscores the reduced likelihood of a strike in the immediate future.

OpenAI gives a base rate of 0.1.The following were considered in order to produce this base rate:

The base rate is derived from historical strike actions involving the International Longshoremen’s Association and contract negotiation outcomes in the U.S. Historically, labor negotiations, once suspended with a tentative agreement, result in a finalized agreement without a strike in the majority of cases. Given the recent tentative agreement reached, the likelihood of a strike in Q1 2025 is low. Additionally, the urgency to maintain economic stability at major U.S. ports often results in pressure to reach agreements that satisfy both parties.

Some potential divergent considerations that might affect the base rate:
While the likelihood of a strike is currently low due to the tentative agreement, unforeseen developments in negotiations could alter this likelihood. If either party becomes dissatisfied with ongoing negotiations, it might renew the risk of a strike. External factors such as economic conditions or political interventions might also influence the outcome. Additionally, internal disagreements within the ILA or pressure from union members could increase strike probability if negotiations stall.

The following chain of events are necessary for the question to resolve positively:
– The International Longshoremen’s Association (ILA) and port employers fail to finalize a long-term contract agreement. Unlikely
– Negotiations between the ILA and port employers break down completely. Unlikely
– The ILA leadership decides to resume strike actions after the current temporary suspension period. Unlikely
– Legal or regulatory barriers do not prevent the strike from happening. Likely

Querying Claude (AI predicts: 0.15 – confidence: 7)
Querying Mistral (AI predicts: 0.15 – confidence: 6)
Querying OpenAI (AI predicts: 0.15 – confidence: 6)
Question Type: Binary
Median from LLMs: 0.15
Base rate: 0.1 (from OpenAI)
SD: 0
Confidence: 6
Conf Mode: Normal
Mellers: 0.07
Reverse Mellers: 0.24
Theory of Mind: 0.25 (What did the LLMs think other LLMs predicted?)
Beta Distribution: 0.001
Close Type: A (B = cautious # closer to 50%; A/C = closer to extremes)
# LLM responses: 3

Model value: 15%

We queried Claude, Mistral, OpenAI. A summary of what the responding AIs considered is as follows: The consensus among the AI analyses is that the likelihood of a strike by the International Longshoremen’s Association (ILA) in Q1 2025 is low. This is primarily due to a tentative agreement reached in January 2025, which historically leads to finalized contracts without striking, coupled with the economic imperative to keep major U.S. ports operating smoothly. However, potential risks could alter this prediction, such as internal union pressures, contentious issues like automation possibly causing negotiations to stall, and unforeseen external economic or political developments that might negatively influence negotiations. Despite these risks, the relatively short time left in the quarter and strong incentives to maintain operations suggest a strike is improbable in the immediate future.





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: 28%
* between 172 and 205: 39%
* between 206 and 240: 28%
* 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:

Recent polling and political developments suggest significant momentum for the Conservative Party heading into potential federal and provincial elections. Conservative leader Pierre Poilievre maintains a substantial lead over Prime Minister Justin Trudeau in opinion polls, with an election expected in the coming months.

There’s an interesting trend of younger voters increasingly supporting the Conservative Party, which political science experts say represents a larger shift in voting patterns. However, recent threats from Donald Trump regarding Canada may be contributing to a slight Liberal Party rebound in polling.
In terms of policy positions, Poilievre has announced plans to slash foreign aid to help build an Arctic military base and boost regional defense capabilities. Meanwhile, in provincial politics, Ontario PC Premier Doug Ford is making headlines by traveling to Washington D.C. during the election campaign amid concerns about potential U.S. tariffs, and has promised a controversial $60 billion tunnel transit project.

The coverage indicates Canada is in pre-election mode at both federal and provincial levels, with the Conservative Party generally well-positioned but facing some new challenges as international factors and domestic policy debates influence voter sentiment.

Summarizing outside newsfeed:
“Recent reports indicate growing momentum for the Conservative Party in Canada as it prepares for possible federal and provincial elections. Conservative leader Pierre Poilievre appears to have a significant lead over Prime Minister Justin Trudeau in opinion polls, with a notable increase in support from younger voters signaling a broader change in voting trends. However, tensions with former U.S. President Donald Trump regarding Canada seem to be aiding a minor rebound for the Liberal Party. On policy matters, Poilievre plans to cut foreign aid to fund an Arctic military base, while Ontario Premier Doug Ford’s controversial initiatives, such as a substantial transit project, draw attention amid his visit to Washington D.C. The situation reflects Canada’s pre-election climate, with the Conservatives seemingly well-positioned yet encountering challenges from international and domestic issues impacting voter sentiment.”

Fact-checking news summary: I’m sorry, but without the list of fact-checked items, I can’t generate the summary you requested. Can you please provide the fact-checking list?

Querying Claude (AI predicts: [“less than 172”: 0.25, “between 172 and 205”: 0.45, “between 206 and 240”: 0.25, “more than 240”: 0.05] – confidence: 5)
Querying Mistral (AI predicts: [“less than 172”: 0.7, “between 172 and 205”: 0.2, “between 206 and 240”: 0.08, “more than 240”: 0.02] – 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: 6)
Question Type: Multiple Choice
Confidence: 6
# LLM responses: 3

Model value:
* less than 172: 28%
* between 172 and 205: 39%
* between 206 and 240: 28%
* more than 240: 5% We queried Claude, Mistral, OpenAI. A summary of what the responding AIs considered is as follows: The Conservative Party of Canada’s potential seat gains in future federal elections are assessed based on historical performances, current polling trends, and political dynamics. Typically, they win between 95 and 200 seats, with the last election netting them 119 seats. A dramatic increase to over 240 seats would be unprecedented without significant voter shift. Most analyses predict a likely outcome of 172 to 205 seats, due to observable momentum and election history. However, factors such as unexpected political events, leadership changes, or regional voting shifts, particularly in provinces like Ontario and Quebec, could affect these predictions. Potential electoral reform, shifts in public opinion due to scandals, and the complexities of the first-past-the-post system add further uncertainties to these projections.

Runtime for the two questions on this page: 247 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