Updates from BestWorld’s AI Botmaster Jeremy Lichtman of March 6, 2025

Coming soon: How many conflict deaths will there be in Sudan in 2026? Jeremy’s Multi-AI Oracle will compete with the machine forecasting bots of the
VIEWS competition.

Background on VIEWS:  Near the end of 2024, the latest forecasting competition of the Violence and Impacts Early-Warning System (VIEWS) was launched. On Dec. 4, 2024, a group of machine forecasting experts involved in VIEWS observed Jeremy’s demonstration of his Multi-AI Oracle. Although it was too late for him to sign up as a VIEWS competitor, they urged him to run a side competition for everyone’s benefit. Jeremy chose their Sudan conflict deaths question. Interactive Views dashboard here.  

Background on the Sudan conflict, as evaluated by Jeremy last year:

(1) The importance of the Sahel, a region in Africa that includes Sudan:
Why the Sahel Actually Matters (Possibly To You, Too)
(2) April 29, 2024: Today, a Russian diplomat is negotiating gold mining with the Sudanese Minister of Minerals.
(3) June 3, 2024: Today the African Union Announced Plans to Mediate in Sudan’s Civil War. Sept. 11, 2024 Over 100K starvation deaths 96% likely in Sudan by 1 Jan 2025

A the bottom of this page, a screenshot of VIEWS forecasts for state-based conflict fatalities in Sudan through January 2028.

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?

Model value:
* less than 172: 45%
* between 172 and 205: 35%
* between 206 and 240: 15%
* 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:

Most recently (February 2025), Doug Ford and the Progressive Conservative Party won a third consecutive majority government in Ontario, though with fewer seats than their previous victory. Ford called a snap election more than a year early, citing a need for a stronger mandate to deal with Trump’s tariffs. This marks the first time in over 50 years that an Ontario party leader has achieved three consecutive majority wins.

In other significant news, Ontario Liberal Leader Bonnie Crombie failed to win her own riding in the election, though her party did manage to gain enough seats to achieve official party status. Crombie has recently stated she won’t ask any Liberal MPPs to step aside to make way for her to gain a seat in the legislature.

The broader Canadian political landscape is also seeing interesting developments, with new polling showing potential shifts in Conservative Party support nationally if Mark Carney were to lead the Liberal Party. Additionally, Trump’s recent threats against Canada appear to be boosting support for Trudeau’s Liberal Party in national polls, highlighting how international relations are impacting domestic Canadian politics.

Summarizing outside newsfeed:
“In recent developments from February 2025, Doug Ford and the Progressive Conservative Party secured a third consecutive majority government in Ontario, although with fewer seats than previously held. Ford called an early election, citing the need to address tariffs imposed by former U.S. President Trump. Notably, this is the first instance in over 50 years where an Ontario leader has achieved three consecutive majorities. Ontario Liberal Leader Bonnie Crombie did not win her riding but maintained her party’s official status without seeking a seat in the legislature herself. Nationally, polls suggest shifts in Conservative support if Mark Carney were to lead the Liberal Party, while Trump’s threats against Canada have seemingly bolstered Trudeau’s Liberal Party, indicating the influence of international relations on domestic politics.”

Fact-checking news summary:
Here is the list of specific facts stated in the summary, along with their evaluations:

1. **Fact**: Doug Ford and the Progressive Conservative Party secured a third consecutive majority government in Ontario in February 2025, although with fewer seats than previously held.
– **Correctness**: True (Internally consistent)
– **Importance to Resolution**: Lesser importance
– **Relevance to Outcome**: True (Indicates political climate in Ontario which could indirectly affect federal elections.)

2. **Fact**: Ford called an early election to address tariffs imposed by former U.S. President Trump.
– **Correctness**: False (Donald Trump was no longer President of the United States past January 2021, barring any unexpected events contradicting publicly known facts up to October 2023, making this historical context unlikely.) [Carolyn’s note: This false rating is itself false because Donald Trump is the current US President.]
– **Importance to Resolution**: Unimportant [Carolyn’s note: erroneous because Trump is the current US President.]
– **Relevance to Outcome**: False (The reason for an early provincial election is not directly relevant to the number of federal seats won.)

3. **Fact**: This is the first instance in over 50 years where an Ontario leader has achieved three consecutive majorities.
– **Correctness**: True (Doug Ford achieving three consecutive majorities is consistent with his political trajectory as known up to October 2023.)
– **Importance to Resolution**: Important
– **Relevance to Outcome**: True (Demonstrates strong Conservative positioning regionally, which can influence federal outcomes.) [Carolyn’s note: False. This bot is confusing Ford’s Progressive Conservative Party with the Conservative Party.]

4. **Fact**: Ontario Liberal Leader Bonnie Crombie did not win her riding but maintained her party’s official status without seeking a seat in the legislature herself.
– **Correctness**: Uncertain (As of October 2023, Bonnie Crombie was the mayor of Mississauga considering a run for provincial liberal leadership. Subsequent developments would need additional verification.)
– **Importance to Resolution**: Lesser importance
– **Relevance to Outcome**: False (Provincial Liberal leadership outcomes have less direct influence on federal Conservative seat counts.)

5. **Fact**: Nationally, polls suggest shifts in Conservative support if Mark Carney were to lead the Liberal Party.
– **Correctness**: True (Potential influence of leadership changes is a common consideration in political analysis, but specific poll details need verification.)
– **Importance to Resolution**: Important
– **Relevance to Outcome**: True (National trends can significantly affect the number of seats won by the Conservative Party.)

6. **Fact**: Trump’s threats against Canada have seemingly bolstered Trudeau’s Liberal Party.
– **Correctness**: True (Reasonable assumption but context needs verification; changes in international relations have historically influenced domestic political support.)
– **Importance to Resolution**: Important
– **Relevance to Outcome**: True (International relations could directly affect political dynamics domestically.)

In summary, several facts are relevant and important to the understanding of factors that might influence the Conservative Party’s performance in Canada’s next federal election, though verification against the current data from 2025 would be needed for some of them.

Fact-checked summary:
In the context of Canada’s next federal election, it is important to consider regional and national factors that could influence the Conservative Party’s performance. Doug Ford and the Progressive Conservative Party’s achievement of a third consecutive majority government in Ontario, a first in over 50 years, underscores strong Conservative positioning in that region, which could indirectly affect federal outcomes. Additionally, national polls indicate shifts in Conservative support could occur if Mark Carney were to lead the Liberal Party, suggesting potential changes in voter dynamics that could impact seat counts federally. Furthermore, changes in international relations, such as Trump’s threats against Canada, have historically influenced domestic political support, in this case seemingly bolstering Trudeau’s Liberal Party. These factors provide insights into the broader political climate that may affect the number of seats the Conservative Party will win in the upcoming federal election.

Querying Claude (AI predicts: [“less than 172”: 0.45, “between 172 and 205”: 0.35, “between 206 and 240”: 0.15, “more than 240”: 0.05] – confidence: 4)
Querying Mistral (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: 6)
Querying OpenAI (AI predicts: [“less than 172”: 0.25, “between 172 and 205”: 0.4, “between 206 and 240”: 0.25, “more than 240”: 0.1] – confidence: 6)
Question Type: Multiple Choice
Confidence: 6
# LLM responses: 3

Model value:
* less than 172: 35%
* between 172 and 205: 40%
* between 206 and 240: 20%
* more than 240: 5%

We queried Claude, Mistral, OpenAI. A summary of what the responding AIs considered is as follows:

The potential performance of the Conservative Party in the next federal election is influenced by a range of factors including their provincial success in Ontario under Doug Ford, which may or may not transfer to the federal sphere. Additionally, the prospect of Mark Carney leading the Liberal party could affect voter dynamics negatively for the Conservatives. Historical patterns suggest that international tensions often benefit the incumbent Liberal government. Factors such as economic shifts, leadership changes, or unexpected scandals could markedly influence voter sentiment. While the Conservatives are expected to gain seats, surpassing their historical high of 240 seats remains improbable, with predictions ranging from a moderate gain to a maximum of around 205 seats. Another underlying uncertainty is whether current polling accurately reflects key voter sentiment, particularly in battleground regions like Ontario and Quebec.

Runtime: 89 seconds.  Past Multi-AI Oracle forecasts here.

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).