Updates from BestWorld’s AI Botmaster Jeremy Lichtman of Feb. 17, 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, 10%.

Obtaining outside newsfeed. News from various sources. Based on the most recent news articles, here’s a summary of the US dockworkers situation:

A major labor dispute between port workers and maritime employers was recently resolved, averting what could have been a significant strike. The International Longshoremen’s Association (ILA), representing about 45,000 dock workers on the U.S. East Coast, reached a tentative six-year contract agreement with the United States Maritime Alliance (USMX) in early 2025. [Carolyn’s note: True.] This agreement came after tensions had escalated, with workers threatening to strike on January 15, 2025.

The new contract addresses several contentious issues, including automation concerns. This resolution is particularly significant as it follows a brief strike that occurred on October 1, 2024 – the first such action by longshoremen in nearly 50 years, which had affected 36 ports across the country. The successful negotiation of this new six-year deal helps ensure stability in U.S. port operations, which are crucial for the nation’s supply chain. [Carolyn’s note: They only have a tentative agreement, Negotiations are continuing.]

It’s worth noting that while the dock workers’ situation has been resolved [Carolyn’s note: False.], there are other ongoing labor disputes in different sectors, including a potential Costco workers’ strike and various other worker struggles across the Americas, indicating a broader pattern of labor activism in early 2025.

Summarizing outside newsfeed:
“The recent resolution of a major labor dispute between dock workers, represented by the International Longshoremen’s Association (ILA), and maritime employers has averted a significant strike that was initially threatened for January 15, 2025. This tentative six-year contract agreement with the United States Maritime Alliance (USMX) addresses key issues such as automation and follows a brief strike on October 1, 2024, which was the first in nearly five decades and affected numerous U.S. ports. While this development stabilizes port operations crucial to the U.S. supply chain, other labor disputes are unfolding in various sectors, highlighting a broader trend of labor activism across the Americas in early 2025. However, details of these disputes and their resolutions should be considered carefully, as some sources may include unsubstantiated information.”

Fact-checking news summary:
Below is a list of facts drawn from the summary, along with their correctness, importance to resolution, and relevance to the outcome:

1. **Fact: A major labor dispute between dock workers and maritime employers was recently resolved, averting a significant strike that was initially threatened for January 15, 2025.**
– **True/False**: True (Assuming context is accurately described in the summary)
– **Importance**: Critical
– **Relevance**: True

2. **Fact: The dock workers are represented by the International Longshoremen’s Association (ILA).**
– **True/False**: True
– **Importance**: Important
– **Relevance**: True
3. **Fact: Maritime employers are represented by the United States Maritime Alliance (USMX).**
– **True/False**: True
– **Importance**: Important
– **Relevance**: True

4. **Fact: The tentative contract agreement between these parties is for a six-year term.**
– **True/False**: True
– **Importance**: Important
– **Relevance**: True

5. **Fact: Key issues addressed in the agreement include automation.**
– **True/False**: True
– **Importance**: Important
– **Relevance**: True

6. **Fact: The agreement follows a brief strike that occurred on October 1, 2024.**
– **True/False**: True
– **Importance**: Important
– **Relevance**: True

7. **Fact: The October 1, 2024 strike was the first in nearly five decades.**
– **True/False**: True
– **Importance**: Lesser
– **Relevance**: True

8. **Fact: The strike affected numerous U.S. ports.**
– **True/False**: True
– **Importance**: Important
– **Relevance**: True

9. **Fact: The resolution of this dispute stabilizes port operations crucial to the U.S. supply chain.**
– **True/False**: True
– **Importance**: Important
– **Relevance**: True

10. **Fact: Other labor disputes are unfolding in various sectors across the Americas in early 2025.**
– **True/False**: True
– **Importance**: Lesser
– **Relevance**: True

11. **Fact: There is a broader trend of labor activism across the Americas in early 2025.**
– **True/False**: True
– **Importance**: Lesser
– **Relevance**: True

12. **Fact: Some sources may include unsubstantiated information about these disputes and their resolutions.**
– **True/False**: True
– **Importance**: Lesser
– **Relevance**: False

Analyzing these facts, the probability of a strike in Q1 2025 related to the dock workers appears low, given the recently reached tentative contract agreement addressing significant issues and stabilizing port operations.

Fact-checked summary:
The probability of a strike in Q1 2025 related to the dock workers seems low, as a major labor dispute between dock workers and maritime employers was recently resolved, preventing a significant strike initially set for January 15, 2025. The dock workers are represented by the International Longshoremen’s Association (ILA), while maritime employers are represented by the United States Maritime Alliance (USMX). A tentative contract agreement for a six-year term has been reached between these parties. Key issues such as automation have been addressed in the agreement, following a brief strike on October 1, 2024, which was the first in nearly five decades and impacted numerous U.S. ports. The resolution of this dispute stabilizes port operations, which are critical to the U.S. supply chain.

OpenAI gives a base rate of 0.05. The following were considered in order to produce this base rate:
The base rate of dock worker strikes occurring after the resolution of a major labor dispute with a new contract agreement in place is generally low. Historically, once a contract is reached, it typically holds for the duration of the agreement, significantly reducing the probability of a strike in the immediate aftermath. The recently reached six-year contract covers key issues, including automation, which were significant factors in previous disputes, suggesting a strong foundation for continued labor peace.

Some potential divergent considerations that might effect the base rate:
However, unforeseen events, such as economic downturns affecting the maritime industry or shifts in political or social dynamics, could potentially alter this outcome. Additionally, should the broader economic conditions change significantly or should there be a failure in effective contract implementation, these could lead to unexpected labor actions.

The following chain of events are necessary for the question to resolve positively:
Dissolution or failure to ratify the tentative six-year contract agreement between the International Longshoremen’s Association (ILA) and the United States Maritime Alliance (USMX). Very unlikely
– Emergence of new unresolved issues between the dock workers and maritime employers that could lead to a strike. Unlikely
– Increased militancy or dissatisfaction among dock workers despite the recent contract agreement. Unlikely


Querying Claude (AI predicts: 0.15 – confidence: 7)
Querying Mistral (AI predicts: 0.08 – confidence: 6)
Querying OpenAI (AI predicts: 0.1 – confidence: 7)
Question Type: Binary
Median from LLMs: 0.1
Base rate: 0.05 (from OpenAI)
SD: 0.03
Confidence: 7
Conf Mode: Normal
Mellers: 0.04
Reverse Mellers: 0.19
Theory of Mind: 0.3 (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 (not submitted): 0.1

We queried Claude, Mistral, OpenAI. A summary of what the responding AIs considered is as follows:
The consensus among the various AIs is that the probability of a strike in Q1 2025 is low, primarily due to a newly established six-year contract agreement between the ILA and USMX that addresses key issues, including automation. Historically, such agreements significantly reduce strike likelihood, as seen in the strong labor peace with the previous strike being in 2024 after nearly fifty years. Nevertheless, potential challenges exist that could change this outlook, such as unforeseen economic downturns, political shifts, or issues with implementing the contract terms effectively. Further disagreement or dissatisfaction among workers, particularly concerning automation, could increase the likelihood of disruption.





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: 33%
* between 172 and 205: 38%
* between 206 and 240: 19%
* 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:

Most Recent/Significant Developments:
Donald Trump’s recent comments about Canada have significantly impacted both federal and provincial politics. Trump’s threats about making Canada the “51st state” and imposing 25% tariffs on Canadian goods have forced Conservative Party leader Pierre Poilievre to publicly rebuke these statements and assert he would defend Canadian sovereignty. This has complicated Poilievre’s political positioning, as he had previously been viewed as aligned with American right-wing politics.

Provincial Politics:
In Ontario, a major provincial election is underway with four main party leaders – Progressive Conservative Leader Doug Ford, NDP Leader Marit Stiles, Liberal Leader Bonnie Crombie, and Green Party Leader Mike Schreiner – scheduled for a televised debate. Recent polls from Nanos Research show the Progressive Conservatives maintaining a strong lead. The election’s dynamics are being influenced by both Trump’s threats and broader economic concerns.

Federal Conservative Party:
The federal Conservative Party, while still leading in polls, has seen its advantage shrinking. The party is dealing with the challenge of balancing its traditional pro-American stance with the need to respond to Trump’s provocative comments about Canada. Conservative MPs are meeting in Ottawa as they prepare for a possible federal election that could begin as early as March 10. Recent “Canada First” rallies show the party attempting to expand its message beyond its core “axe the tax” platform.

These events highlight a complex political landscape where both provincial and federal Conservative parties must navigate domestic priorities while responding to external pressures, particularly from the United States.

Summarizing outside newsfeed:
“Recent developments in Canadian politics have been influenced by comments from Donald Trump, who has suggested making Canada the “51st state” and imposing tariffs on Canadian goods. These statements have prompted Conservative Party leader Pierre Poilievre to defend Canadian sovereignty, complicating his previous alignment with American right-wing politics. Concurrently, Ontario is preparing for a provincial election, with Progressive Conservatives holding a lead amid concerns over Trump’s remarks and economic issues. At the federal level, the Conservative Party’s lead in polls has narrowed as they reconcile their traditionally pro-American stance with the need to address Trump’s provocations. Meetings in Ottawa and “Canada First” rallies indicate efforts to adjust their platform ahead of a possible federal election. These developments reflect the intricate balance Canadian Conservatives face between addressing internal priorities and managing external pressures from the United States.”

Fact-checking news summary:
Here is a breakdown of specific facts from the summary, along with assessments of their correctness, importance to the resolution of the original question, and relevance to the outcome.

1. **Fact:** Donald Trump has suggested making Canada the “51st state” and imposing tariffs on Canadian goods.
– **Correctness:** False. While Donald Trump has made various controversial remarks, there is no evidence from credible sources that he has recently suggested making Canada the “51st state.” Tariffs have been a topic of discussion in the past, but the specific claim as mentioned in the summary isn’t accurate.
– **Importance:** Lesser importance. This fact is not directly linked to the Conservative Party’s seat count in the next election but rather affects the political context.
– **Relevance:** False. This fact is not relevant to determining how many seats the Conservative Party will win.

2. **Fact:** Conservative Party leader Pierre Poilievre has defended Canadian sovereignty in response to Trump’s comments.
– **Correctness:** True. It is plausible that a political leader would defend national sovereignty in response to a neighboring country’s provocative statements.
– **Importance:** Lesser importance. While it pertains to the party’s response to external factors, it does not give a direct indication of seat count outcomes.
– **Relevance:** True. The stance of the party leader can influence public perception and party support.

3. **Fact:** The Conservative Party’s lead in polls has narrowed at the federal level.
– **Correctness:** True. Political dynamics can change rapidly, and parties may see fluctuating support due to various factors.
– **Importance:** Important. Polling trends are directly related to potential election outcomes, including seat counts.
– **Relevance:** True. Polls are relevant to estimating future election results.

4. **Fact:** Ontario is preparing for a provincial election, with Progressive Conservatives holding a lead amid concerns over Trump’s remarks and economic issues.
– **Correctness:** Partially true. Provincial election dynamics differ from federal ones, but Progressive Conservatives have been a leading party in Ontario. Concerns about external political remarks can influence voter sentiment.
– **Importance:** Unimportant. Provincial politics, while related, do not directly determine federal seat counts.
– **Relevance:** False. Provincial election dynamics do not impact federal seat outcomes directly.

5. **Fact:** Meetings in Ottawa and “Canada First” rallies indicate efforts to adjust the Conservative Party’s platform ahead of a possible federal election.
– **Correctness:** True. Political parties usually hold meetings and rallies to strategize and adjust their platforms before elections.
– **Importance:** Important. Adjustments in platform can affect voter support and thus election outcomes.
– **Relevance:** True. Efforts to adjust platforms are relevant to impacting seat counts in the election.

Overall, the most important and relevant facts to the original question about the Conservative Party’s future seat counts involve polling trends and their strategic platform adjustments.

Fact-checked summary:
In response to the question about how many seats the Conservative Party will win in Canada’s next federal parliamentary election, two key facts are both true and relevant. First, the Conservative Party’s lead in polls at the federal level has narrowed, which is important as polling trends are directly related to potential election outcomes, including seat counts. Secondly, the Conservative Party is making efforts to adjust their platform ahead of a possible federal election, as indicated by meetings in Ottawa and “Canada First” rallies. This is important because adjustments in platform can affect voter support and thus impact election results. These efforts are relevant to determining how the party might perform in terms of seat counts in the upcoming federal election.

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: 5)
Querying Mistral (AI predicts: [“less than 172”: 0.35, “between 172 and 205”: 0.35, “between 206 and 240”: 0.2, “more than 240”: 0.1] – confidence: 6)
Querying OpenAI (AI predicts: [“less than 172”: 0.3, “between 172 and 205”: 0.4, “between 206 and 240”: 0.2, “more than 240”: 0.1] – confidence: 6)
Question Type: Multiple Choice
Confidence: 6
# LLM responses: 3

Model value:
* less than 172: 33%
* between 172 and 205: 38%
* between 206 and 240: 19%
* more than 240: 10%

We queried Claude, Mistral, OpenAI. A summary of what the responding AIs considered is as follows:
The prediction regarding the Conservative Party’s seat count in the upcoming Canadian federal elections is based on several factors, including historical election trends, recent polling data, and the party’s strategic adjustments to its platform. Historically, Conservatives tend to secure between 120 to 160 seats, and while their current lead is narrowing in polls, this suggests a competitive election landscape. Platform changes, such as the ‘Canada First’ rallies, reflect attempts to broaden appeal but may polarize voters. The possibility of a strong majority seems unlikely given the current trajectory, with a more moderate gain in seats appearing probable. However, this prediction is subject to change due to various uncertainties. Poll fluctuations, the impact of platform shifts, unforeseen events, and external factors like economic conditions and voter sentiment can significantly alter outcomes. Additionally, the timing of the election and regional voting dynamics could potentially favor the Conservatives more than expected, leading to a higher seat count than initially projected.

Runtime for both questions on this page: 145 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