Sudan updates from AI Botmaster Jeremy Lichtman of April 23, 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: 3%
* Between 5000 and 8000: 5%
* Between 8000 and 12000: 15%
* More than 12000: 74%
Obtaining outside data.
Checking internet sources, using keywords: Sudan conflict deaths 2025
Results from around the web:

Okay, let’s tackle this query about the Sudan conflict deaths in 2025. The user wants current web results from news sites, relevant Wikipedia pages, official websites, and prediction markets. They also want tables of data and time series if available.

First, I need to check the provided search results. The most recent one is from Human Rights Watch dated April 13, 2025, which mentions two years into the conflict. The other sources are from December 2024, February 2025, and April 2025. None of them go beyond April 2025, and the current date is April 23, 2025. So there’s a gap in data from April to the current date.

Looking at the sources:
1. ACLED (Dec 2024) reports over 28,700 fatalities by November 2024, with estimates up to 150,000.
2. Science.org (Feb 2025) cites varying estimates from 20,000 to 150,000, highlighting difficulty in data collection.
3. HRW (April 2025) states tens of thousands of civilians died, with both sides committing atrocities.
4. CFR’s Global Conflict Tracker mentions the former U.S. envoy’s estimate of 150,000 killed since the start in 2023.
Notably, all sources emphasize the challenge in getting accurate numbers due to the chaotic situation, blocked access, and underreporting. The 150,000 figure is a high estimate, while the lower end is around 20,000. However, ACLED’s 28,700 is specific to reported fatalities but notes it’s an underestimate.

The user also asked for prediction market data, but none of the provided sources mention sites like Kalshi or Polymarket. So I can’t include that. For tables, I can summarize the available data from the sources. Time series data isn’t directly provided, but I can structure the available figures into a period-based table with the estimates.

I need to make sure to cite each source properly. Since the current date is April 2025, the latest info is from HRW in April 2025, which doesn’t give a specific number but mentions “tens of thousands.” The most specific recent figure is from ACLED in December 2024 with 28,700 reported, but they also reference the 150,000 estimate. The CFR source from an unspecified date (but mentioned the conflict entering its third year, so 2025 also cites 150,000.

In the answer, I should highlight the range of estimates, the sources of discrepancy, and the humanitarian impact. Since there’s no data beyond April 2025, I can’t provide 2025-specific death tolls beyond what’s already mentioned up to April. The time series table can show the progression from 2023 to April 2025 with the available data points, adding change, mean, etc. But since the data points are sparse, some stats like standard deviation might not be feasible. I’ll have to calculate what’s possible based on the given numbers.

Additionally, the user requested tables in tabbed or comma-separated format, but the answer should use markdown tables. I’ll format them accordingly, making sure to note the sources for each figure. The key is to present the information clearly, acknowledge the uncertainty, and cite each source properly.

The Sudan conflict, ongoing since April 2023, has resulted in catastrophic human losses and displacement. Estimates of deaths vary widely due to challenges in data collection, with figures ranging from **20,000** to **150,000** by early 2025[2][4]. Below is a synthesis of available data and key developments:
—
### **Reported Fatalities and Trends**
– **ACLED** recorded **28,700+ reported fatalities** by November 2024, including over 7,500 civilians[1]. This is considered a significant underestimate, with indirect deaths (starvation, disease) far exceeding direct combat fatalities[2].
– **Human Rights Watch** (April 2025) states “tens of thousands of civilians have died,” emphasizing atrocities by both the Sudanese Armed Forces (SAF) and Rapid Support Forces (RSF)[3].
– A **U.S. envoy estimate** suggests **150,000 total deaths** since the war began, reflecting indirect mortality from displacement, destroyed infrastructure, and aid blockades[4].

—
### **Humanitarian Impact**
– **Displacement**: Over **14 million displaced** (30% of Sudan’s population), with 3 million fleeing to Chad, Ethiopia, and South Sudan[4].
– **Aid Blockades**: Both sides weaponize starvation, blocking food and medical supplies to 30 million in need[2][3].
– **Infrastructure Destruction**: Hospitals, schools, and utilities targeted, exacerbating famine and disease[2][4].
—
### **Regional and International Involvement**
– **RSF** receives suspected drone and weapon supplies from the **UAE**, while **SAF** is backed by Egypt, Russia, and Iran[1].
– The UN and U.S. accuse the RSF of **ethnic cleansing in Darfur** and genocide against non-Arab groups[2][3].
—
### **Data Challenges**
– **Underreporting**: Humanitarian groups face hostility, with many data collectors “dead or displaced”[2].
– **Methodology**: Satellite imagery and mortality models are used to estimate deaths, but gaps persist[2].
—
This conflict remains among the deadliest globally, with no resolution in sight as both sides reject mediation[3][4]. The true death toll likely lies at the higher end of estimates due to unrecorded indirect mortality.

OpenAI gives a base rate of probability of death toll exceeding 20,000 based on historical conflict data
The question difficulty is rated 8 (0 to 10)
Historical weighted factors include:
Past conflict mortality rates, 0.4
Current humanitarian conditions, 0.3
International intervention, 0.2
Media coverage accuracy, 0.1

A Bayesian calculation could be performed as follows:
Bayesian probability updates calculated using historical factors with current updates from Human Rights Watch, ACLED, and CFR estimates. Prior probability set according to ACLED. Posterior updated based on HRW, CFR, and Science.org reports indicating higher estimates.

Bayesian base rate: 0.85 Sufficient news to provide a good forecast? 0 (0 or 1)
News is relevant, topical and unbiased? 1 (0 or 1)
Question classification: scenario_based_forecast
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 determined from historical analyses of similar conflicts in the region, considering the longevity, scale, and intensity of the conflict. Data from ACLED and Human Rights Watch suggests a consistent pattern of high fatality rates indicative of ongoing and unresolved conflicts.

Ideally, the news feed would contain the following sorts of information for a better forecast:
More precise, granular data on regional casualties, international boots-on-the-ground reports, and real-time technological observations could improve forecast accuracy.

Some potential divergent considerations that might affect the base rate:
Factors like successful peace negotiations, increased humanitarian access, or significant shifts in military dynamics could lead to significantly lower or higher death tolls than predicted. The volatile political situation in neighboring regions might also impact the conflict’s trajectory.

The following chain of events are necessary for the question to resolve positively:
– Continued conflict between SAF and RSF Very Likely
– Humanitarian aid blockades Probable
– No international diplomatic resolution Likely

Querying Claude (AI predicts: [“Less than 1000”: 0.01, “Between 1000 and 3000”: 0.02, “Between 3000 and 5000”: 0.03, “Between 5000 and 8000”: 0.04, “Between 8000 and 12000”: 0.15, “More than 12000”: 0.75] – 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”: 0.24, “Between 8000 and 12000”: 0.3, “More than 12000”: 0.3] – confidence: 6)

Querying OpenAI (AI predicts: [“Less than 1000”: 0.01, “Between 1000 and 3000”: 0.02, “Between 3000 and 5000”: 0.02, “Between 5000 and 8000”: 0.05, “Between 8000 and 12000”: 0.1, “More than 12000”: 0.8] – confidence: 5)

Question Type: Multiple Choice
Confidence: 6
MAPD: Avg: 0.11222222222222, Max: 0.33333333333333
# LLM responses: 3

Model value:
* Less than 1000: 1%
* Between 1000 and 3000: 2%
* Between 3000 and 5000: 3%
* Between 5000 and 8000: 5%
* Between 8000 and 12000: 15%
* More than 12000: 74%

The reasoning across various AI analyses suggests that the conflict in Sudan is severe, with estimates of fatalities ranging from 20,000 to over 150,000, and continued high casualty figures expected into 2025 due to ongoing fighting between the SAF and RSF, and humanitarian aid blockades affecting millions. However, there are factors that could lower the death toll, such as successful peace negotiations, improved humanitarian access, or international intervention that could lead to a ceasefire. The volatile political situation and potential for military shifts make the predictions uncertain, and the actual number of fatalities might be underreported due to data collection issues. Overall, while high fatalities are expected, the situation remains fluid and subject to change based on diplomatic or military developments.

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/