Sudan updates from AI Botmaster Jeremy Lichtman of May 2, 2025

How many conflict deaths will there be in Sudan in 2025?

Jeremy’s most recent version of his Multi-AI Oracle is a side competitor with the machine forecasting bots of the VIEWS competition.

Here’s what Jeremy‘s latest version of his Multi-AI Oracle predicts:

Model value:
* Less than 1000: 1%
* Between 1000 and 3000: 2%
* Between 3000 and 5000: 7%
* Between 5000 and 8000: 15%
* Between 8000 and 12000: 25%
* More than 12000: 50%

Here’s how Jeremy’s Multi-AI Oracle says it arrived at these probabilities:

Obtaining outside data.
Checking internet sources, using keywords: Sudan conflict deaths 2025
Results from around the web: {think}

Okay, let’s tackle this query about the Sudan conflict deaths in 2025. The user wants current web results from reliable sources and a summary with tables. First, I need to check the search results provided.

Looking at the sources, they all mention the conflict in Sudan but vary in their death toll estimates. ACLED [1][5] reports over 28,700 fatalities by November 2024, including 7,500 civilians. Science.org [2] cites similar numbers but notes that some estimates go up to 150,000 when including starvation and disease. CFR [3] mentions 50 civilians killed in March 2025, and Genocide Watch [4] states 61,000 deaths in Khartoum alone, with 90% unrecorded. The Guardian via [4] also mentions 150,000 civilian deaths by November 2024.

I need to summarize these findings. Start with an overview of the conflict, then break down the death toll by source, highlighting the range of estimates. The user asked for tables, so I’ll create one comparing the different reports. Another table could show the time series data, but the sources don’t provide monthly breakdowns. Instead, I’ll note that time series data isn’t available and focus on the available figures.

Including the URLs at the end as requested. Make sure all citations are correctly referenced and the tables are formatted properly. Check that the answer addresses all parts of the query: summary, tables, and sources.

The ongoing civil war in Sudan, which escalated in April 2023 between the Sudanese Armed Forces (SAF) and Rapid Support Forces (RSF), has resulted in catastrophic human losses. By early 2025, estimates of conflict-related deaths vary significantly due to challenges in data collection, with sources reporting figures ranging from **28,700 to over 150,000 fatalities** when accounting for indirect causes like starvation and disease[1][2][4].

### Key Findings on Conflict Deaths
– **ACLED Data (December 2024):**
– 28,700+ reported fatalities (including 7,500 civilians killed in direct attacks)
– Conflict ranked as the **fourth-deadliest globally** by late 2024[1][5].
– **Genocide Watch (January 2025):**
– 61,000+ deaths in Khartoum alone (26,000 from direct violence)
– 90% of deaths in Khartoum unrecorded[4].
– **Scientific Estimates (February 2025):**
– Over 150,000 deaths when including indirect causes[2][4].

### Civilian Impact
– 30% of Sudan’s population (14 million people) displaced[1].
– Both SAF and RSF accused of using **starvation as a weapon**, blocking humanitarian aid to 30 million people[2].

### Comparative Fatality Data Table

*Note: Time series data is unavailable due to inconsistent reporting.*

### Sources Used
1. https://acleddata.com/conflict-watchlist-2025/sudan/
2. https://www.science.org/content/article/how-many-have-died-sudan-s-civil-war-satellite-images-and-models-offer-clues
3. https://www.cfr.org/global-conflict-tracker/conflict/power-struggle-sudan
4. https://www.genocidewatch.com/single-post/sudan-genocide-emergency-january-2025
5. https://acleddata.com/africa/horn-of-africa/sudan/ Discrepancies in death tolls stem from limited access to conflict zones and the exclusion of indirect fatalities in official counts. Most sources emphasize that reported numbers are likely severe underestimates[2][4].

OpenAI gives a base rate of likelihood of death toll exceeding specified categories
The question difficulty is rated 9 (0 to 10)
Historical weighted factors include:
Conflict intensity from 2023 to date, 0.3
Historical underreporting in conflict zones, 0.2
Lack of humanitarian intervention, 0.2
Global geopolitical responses, 0.1
Economic conditions in Sudan, 0.2
A Bayesian calculation could be performed as follows:
Updated likelihood is calculated using prior beliefs based on historical factors and adjusted with evidence from recent news and reports indicating ongoing high fatalities. The Bayesian update would adjust the base rate upward given additional indirect fatalities reported and ongoing violent conditions, possibly increasing the rate to approximately 0.8.
Bayesian base rate: 0.8
Sufficient news to provide a good forecast? 1 (0 or 1)
News is relevant, topical and unbiased? 1 (0 or 1)
Question classification: scenario_based_forecast
Expected time (days) until question close: 240 (Carolyn’s note: As is common among GenAI bots, this one can’t count. The actual remaining days, including today, are 245.)

The following were considered in order to produce this base rate:
The ongoing conflict in Sudan has shown significant fatalities based on previous reports, with a trend of increasing violence and humanitarian crises impacting the death toll. Historical data suggests underreported fatalities and challenges in data collection, which inform a higher base rate.

Ideally, the news feed would contain the following sorts of information for a better forecast:
More granular data concerning monthly fatalities, on-ground reports about humanitarian aid effectiveness, and geopolitical shifts impacting Sudan would be helpful. Verification from multiple independent sources for reported fatalities would improve forecast accuracy.

Some potential divergent considerations that might affect the base rate:
Potential peace talks or interventions by global political bodies could reduce conflict intensity and related fatalities. Conversely, further destabilization or conflict spillover from neighboring regions could increase the death toll.

The following chain of events are necessary for the question to resolve positively:
– The ongoing conflict in Sudan continues with the same intensity or worsens, likelihood: likely.
– Lack of successful peace negotiations, likelihood: likely.
– Continued insufficient humanitarian aid reaching affected regions, likelihood: very likely.
– Persistent underreporting and limited access for accurate data collection in conflict zones, likelihood: highly likely.

Querying Claude (AI predicts: [“Less than 1000”: 0.01, “Between 1000 and 3000”: 0.02, “Between 3000 and 5000”: 0.07, “Between 5000 and 8000”: 0.15, “Between 8000 and 12000”: 0.25, “More than 12000”: 0.5] – confidence: 6)

Querying Mistral (AI predicts: [“Less than 1000”: 0.01, “Between 1000 and 3000”: 0.05, “Between 3000 and 5000”: 0.14, “Between 5000 and 8000”: 0.25, “Between 8000 and 12000”: 0.3, “More than 12000”: 0.25] – confidence: 6)

Querying OpenAI (AI predicts: [“Less than 1000”: 0.01, “Between 1000 and 3000”: 0.02, “Between 3000 and 5000”: 0.05, “Between 5000 and 8000”: 0.12, “Between 8000 and 12000”: 0.2, “More than 12000”: 0.6] – confidence: 8)

Question Type: Multiple Choice
Confidence: 6
MAPD: Avg: 0.077777777777778, Max: 0.23333333333333
# LLM responses: 3

Model value:
* Less than 1000: 1%
* Between 1000 and 3000: 2%
* Between 3000 and 5000: 7%
* Between 5000 and 8000: 15%
* Between 8000 and 12000: 25%
* More than 12000: 50%

The summaries produced by multiple AIs converge on the assessment that the conflict in Sudan is both deadly and protracted, with significant mortality figures reported by different sources ranging from direct conflict fatalities to those resulting from starvation and disease. Estimates of fatalities vary widely, with ACLED reporting over 28,700 deaths by late 2024, while Genocide Watch suggests numbers as high as 150,000 when indirect causes are considered. The situation remains dire, with ongoing violence and inadequate humanitarian assistance compounding the crisis. Predictions for 2025 expect continued high casualty numbers, exceeding 12,000. However, there are uncertainties due to potential breakthroughs in peace negotiations, increased humanitarian aid, better data collection, and diplomatic efforts, all of which might influence the actual death toll. Concerns about the reliability of current data due to potential overreporting or underreporting must also be considered, which adds a layer of uncertainty to these projections.

Runtime: 70 seconds.

Past forecasts on Sudan’s conflict fatalities —>

Guide to Multi-AI Oracle’s Reports (some of these only apply to older versions)
Bayesian calculation: a mathematical technique that helps determine the conditional probability of an event based on prior knowledge and new evidence.
MAPD: Mean Absolute Percentage Deviation calculates the average percentage difference between actual values and predicted values, providing a relative measure of error.
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, but sometimes it fails to calculate this. Additionally, we calculate a Bayesian base rate which takes into account recent data. These results are sometimes different.
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.
# LLM Responses: The count of LLMs that responded.
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 Revers

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, during a telecon, a group of machine forecasting experts involved in VIEWS observed Jeremy’s demonstration of his Multi-AI Oracle. Although it was too late for Jeremy 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. Currently, the average of the twenty VIEWS competitors predict that Sudan conflict deaths will decrease sharply this year, as shown by their graph below.



Background on the Sudan conflict, as evaluated by the team of Jeremy Lichtman and Carolyn Meinel:
(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
(4) Sept. 11, 2024 Over 100K starvation deaths 96% likely in Sudan by 1 Jan 2025

Below, map of control in Sudan’s civil war as of April 15, 2025.

Below, before and after pictures of the devastation of the civil war in Sudan.

https://www.alnilin.com/
https://www.alrakoba.net/
https://www.altaghyeer.info/ar/
https://www.altaghyeer.info/en/
https://www.alttahrer.com/
https://www.alzaeemsd.com/
https://www.assayha.net
https://www.cover-sd.com/
https://kushnews.net/
https://rakobanews.com
https://www.sudanakhbar.com/
https://sudanjem.com/
https://suna-sd.net/en
https://sudantimes.net/
https://www.sudantribune.net/
https://www.sudantribune.com/
https://sudaneseonline.com/
https://www.sudanile.com/
https://sudanow-magazine.net/
https://www.sudaress.com/
https://www.tagpress.net/