Sudan updates from AI Botmaster Jeremy Lichtman of April 22, 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: (Carolyn’s note: Both Jeremy and I agree, these probabilities are, so far, just an experiment. It is too early to know how good these will turn out to be)
* Less than 1000: 1%
* Between 1000 and 3000: 2%
* Between 3000 and 5000: 5%
* Between 5000 and 8000: 12%
* Between 8000 and 12000: 20%
* More than 12000: 60%
Obtaining outside data.
Checking internet sources, using keywords: Sudan conflict deaths 2025
Results from around the web: {think}

Okay, I need to address the user’s query about finding current web results related to Sudan conflict deaths in 2025 and summarize the contents, including any relevant data tables. Let me start by reviewing the provided search results to extract the necessary information.

First, looking at the search results:
1. **Source [1]** from science.org (2025-02-26) mentions that death estimates range from 20,000 to 150,000, emphasizing that many die from starvation and disease rather than direct violence. It also notes the use of starvation as a weapon by both SAF and RSF.
2. **Source [2]** from ACLED (2024-12-12) reports over 28,700 fatalities by November 2024, with some estimates as high as 150,000. It also provides data on displacement and foreign involvement in the conflict.
3. **Source [3]** from Human Rights Watch (2025-04-13) states tens of thousands of civilians have died, with both sides committing atrocities and war crimes. They emphasize the need for a protection mission.
4. **Source [4]** from CFR’s Global Conflict Tracker mentions a death toll estimate of up to 150,000 by the former U.S. envoy and highlights the displacement crisis.

The user wants a summary of these sources and tables of relevant data. Since all sources are from late 2024 to April 2025, they’re current. The main challenge is varying death toll estimates and different aspects covered (direct deaths, displacement, foreign involvement).

I need to structure the answer starting with a summary of the death toll ranges, causes of death, and key actors. Then, create a table summarizing the data points from each source. Additionally, the user requested time series data, but the sources don’t provide monthly breakdowns, so I can’t generate a detailed time series. However, I can note the period covered (up to April 2025) and the reported figures.

I must ensure citations are correctly applied after each relevant sentence. Also, check if any market prediction sites are mentioned, but the provided sources don’t include Kalshi, Metaculus, or Polymarket, so I’ll note their absence.

Finally, format the answer with headers, lists, and tables as per the instructions, avoiding any markdown syntax mistakes. The ongoing civil war in Sudan, which began in April 2023, has led to catastrophic human losses, though precise death tolls remain contested. Below is a synthesis of key findings from recent reports and data sources:
—
### **Reported Death Toll Estimates**
– **20,000–150,000 deaths** (as of February 2025), with starvation and disease surpassing direct combat fatalities[1][4].
– **28,700+ documented fatalities** (as of November 2024), including 7,500 civilians killed in direct attacks[2].
– Over **150,000 deaths** cited by former U.S. envoy Tom Perriello, though methodologies for this estimate are unclear[4].
—
### **Primary Causes of Mortality**
1. **Violence**:
– Both the Sudanese Armed Forces (SAF) and Rapid Support Forces (RSF) have committed war crimes, including ethnic cleansing in Darfur[3].
– Drone strikes, artillery, and mass executions target civilians[2][3].
2. **Starvation and Disease**:
– Blockades on aid by SAF and RSF have exacerbated famine and preventable deaths[1][3].
– Over **30 million people** (≈60% of Sudan’s population) require humanitarian assistance[2][4].
—

### **Displacement and Humanitarian Crisis**
– **14 million displaced** (≈30% of the population), including 3 million refugees in Chad, Ethiopia, and South Sudan[2][4].
– **90% of hospitals** in conflict zones are nonfunctional, worsening health crises[1][3].

—
### **Notable Omissions**
– No data from prediction markets (e.g., Kalshi, Polymarket) was found in the provided sources.
– Time-series statistics (e.g., monthly trends) are unavailable due to reporting gaps and restricted access for researchers[1][3].

The Sudanese conflict remains one of the deadliest globally, with accountability mechanisms and humanitarian responses critically lacking[3][4].

OpenAI gives a base rate of range likelihood (Carolyn’s note: OpenAI failed to return a value.)
The question difficulty is rated 8 (0 to 10)
Sufficient news to provide a good forecast? 1 (0 or 1)
News is relevant, topical and unbiased? 1 (0 or 1)
Question classification: reference_class
Expected time (days) until question close: 365 (Carolyn’s note: This is an example of the difficulty all Generative AIs based on large language models can have with math that human eight-year-olds can do, The real number is 252 counting today, April 23.)
The following were considered in order to produce this base rate:
The base rate is influenced by historical data on conflict-induced fatalities in Sudan and neighboring regions. Previous conflicts in Sudan, such as the Darfur conflict, suggest that high casualty figures are plausible given the conditions outlined by recent reports. Additionally, the complex nature of multi-causal sources of mortality (violence, starvation, disease) complicates exact counts, leading to wide ranges in estimates.

Ideally, the news feed would contain the following sorts of information for a better forecast:
Additional detailed breakdowns of mortality statistics by region, cause, and time would enhance the forecast’s precision. Information from ground-based assessments by humanitarian organizations and possible future international investigations would also be beneficial.

Some potential divergent considerations that might affect the base rate:
Variations in reporting standards and the potential for inflated figures due to political motives may lead to discrepancies in reported death tolls. Satellite and modern technological monitoring may improve accuracy slightly compared to historic conflicts, but access and data integrity issues still pose significant challenges.

The following chain of events are necessary for the question to resolve positively:
– Confirmation of the total number of deaths in the Sudan conflict reaching a specified range by April 2025. Current estimates suggest that a final verification or acceptance of such a number is likely due to ongoing conflict dynamics and humanitarian reporting. (Likelihood: High)
– The collection and aggregation of reliable data sources regarding violence-related fatalities, starvation, and disease across the region. Ongoing verification is difficult due to instability but remains crucial. (Likelihood: Moderate)
– Independent monitoring groups and international bodies corroborate reports on the death toll, possibly within the higher range estimates given political interests and resource constraints. (Likelihood: Moderate)

Querying Claude (AI predicts: [“Less than 1000”: 0.01, “Between 1000 and 3000”: 0.02, “Between 3000 and 5000”: 0.05, “Between 5000 and 8000”: 0.07, “Between 8000 and 12000”: 0.15, “More than 12000”: 0.7] – confidence: 7)

Querying Mistral (AI predicts: [“Less than 1000”: 0.01, “Between 1000 and 3000”: 0.05, “Between 3000 and 5000”: 0.1, “Between 5000 and 8000”: 0.2, “Between 8000 and 12000”: 0.3, “More than 12000”: 0.34] – 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: 7)

Question Type: Multiple Choice
Confidence: 7
MAPD: Avg: 0.08, Max: 0.24
# LLM responses: 3

Model value:
* Less than 1000: 1%
* Between 1000 and 3000: 2%
* Between 3000 and 5000: 5%
* Between 5000 and 8000: 12%
* Between 8000 and 12000: 20%
* More than 12000: 60%

The ongoing conflict in Sudan has resulted in a significant number of casualties, with estimates ranging from 20,000 to 150,000 due to direct violence as well as indirect causes like starvation and disease. Despite these high figures, there is considerable uncertainty due to inconsistent reporting standards, limited access to conflict zones, and potential inflation of numbers for political purposes. The current humanitarian crisis, characterized by widespread starvation and a collapsed medical infrastructure, continues to exacerbate the situation, making high mortality rates likely through 2025. However, hopes for a reduced death toll exist if international pressure leads to a ceasefire, improved humanitarian access alleviates crises, or population displacement moves people to safer areas. The situation remains fluid, with potential changes in conflict dynamics and humanitarian responses possibly affecting future casualty figures.

Past forecasts on Sudan’s conflict fatalities —>

Guide to Multi-AI Oracle’s Reports (some of these only apply to older versions)
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. 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 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.

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/