Ukraine Conflict Deaths? Botmaster Jeremy Lichtman’s forecast, Oct. 9, 2025

How many state-based conflict deaths (total of all civilian and combat deaths, including both Ukrainian and Russian combatants) will be reported by ACLED in Ukraine in October 2025?

Jeremy’s Multi-AI Oracle predicts today:

Less than 500: 5%
Between 500 and 1,000: 20%
Between 1,000 and 1,500: 35%
Between 1,500 and 2,000: 25%
Greater than 2,000: 15%

10–13 minutes read

Obtaining outside data.
Checking internet sources, using keywords: Ukraine conflict deaths October 2025
News from various sources:

In October 2025, the conflict in Ukraine continues to escalate, resulting in significant casualties and human rights concerns. Several key developments were reported:
1. **French Photojournalist Killed**: Antoni Lallican, a French photojournalist working for the Hans Lucas agency, was killed by a drone strike in the Donbas region of Ukraine on October 3. French President Emmanuel Macron and the International Federation of Journalists (IFJ) have condemned the attack. It’s noted as potentially the first instance where a drone strike specifically targeted a journalist during the conflict.
2. **Investigation into War Crimes**: Following Lallican’s death, French prosecutors have launched a war crimes investigation, categorizing the attack as a deliberate violation of international humanitarian law.
3. **Civilian Casualties**: The United Nations reported a sharp increase in civilian casualties in 2025, with more than 50,000 civilians killed or injured since the conflict began in 2022. Of these, over 3,000 are children. Attacks on civilian infrastructure such as schools, hospitals, and shelters have intensified, further endangering Ukrainian civilians.
4. **Human Rights Violations**: The Office of the High Commissioner for Human Rights (OHCHR) has documented numerous human rights violations, including torture and extrajudicial executions, primarily by Russian forces in occupied territories. Arbitrary detentions and enforced disappearances of Ukrainian civilians and POWs were reported. The Russian legal system’s amendments have led to increased impunity for military personnel.
5. **Appeal to End the Conflict**: UN human rights chief Volker Türk urged both sides to halt hostilities and respect international law, emphasizing the catastrophic human toll and the risk of escalating regional instability.
These developments underline the urgent call for international intervention and resolution to halt the mounting human toll and violations amid the ongoing conflict in Ukraine.

Fact-checking news summary:
Let’s break down the specific facts from the summary, check their consistency and correctness, and determine their importance and relevance to the original question of how many state-based conflict deaths will be reported in October 2025:
1. **French Photojournalist Killed**: Antoni Lallican, a French photojournalist, was killed by a drone strike in the Donbas region of Ukraine on October 3. This act was condemned by French President Macron and the IFJ, and it is noted as a potentially first targeted strike on a journalist in the conflict.
– **Correctness**: True (Assuming the summary is factual, although the external truth cannot be verified here).
– **Importance**: Lesser (this does not directly provide a count of deaths).
– **Relevance**: True (it relates to the context of conflict escalation but does not directly impact the death count).
2. **Investigation into War Crimes**: French prosecutors have launched an investigation, labeling the attack on Lallican as a deliberate violation of international humanitarian law.
– **Correctness**: True (Internally consistent, assuming summary accuracy).
– **Importance**: Unimportant (does not affect the death tally).
– **Relevance**: False (It does not help determine how many have died).
3. **Civilian Casualties**: The UN reported a sharp increase in civilian casualties, with more than 50,000 civilians killed or injured since the conflict began in 2022, including over 3,000 children. Civilian infrastructure attacks have intensified.
– **Correctness**: True (Internally consistent and plausible given the conflict’s scope; external verification can’t be made here).
– **Importance**: Critical (provides context for the scale of casualties, which is crucial for estimating total deaths).
– **Relevance**: True (directly relates to fatality numbers).
4. **Human Rights Violations**: OHCHR documented human rights abuses by Russian forces, including torture, extrajudicial executions, arbitrary detentions, and enforced disappearances. Russian legal amendments have increased military impunity.
– **Correctness**: True (assuming summary accuracy; plausible given previous reports).
– **Importance**: Important (indicates conflict severity, affecting casualty numbers).
– **Relevance**: True (provides context that could affect death counts).
5. **Appeal to End Conflict**: UN human rights chief Volker Türk appealed for a halt in hostilities and adherence to international law, highlighting human cost and potential regional instability.
– **Correctness**: True (internally consistent within the context of similar appeals).
– **Importance**: Lesser (it doesn’t provide a count of current or projected deaths).
– **Relevance**: True (contextualizes the conflict severity and potential for increased casualties).
Overall, for the specific purpose of estimating conflict deaths reported by ACLED in October 2025, fact 3 is the most critical and relevant, while facts 1, 4, and 5 provide supplementary context on conflict dynamics potentially affecting casualty rates.

Fact-checked summary:
In addressing the question of how many state-based conflict deaths will be reported by ACLED in Ukraine in October 2025, the most directly relevant and critical information is the UN report highlighting a significant increase in civilian casualties, with over 50,000 civilians killed or injured since the conflict began in 2022, including more than 3,000 children, due to intensified attacks on civilian infrastructure. This fact underscores the scale of casualties, which is crucial for estimating total deaths. Additionally, the human rights violations documented by OHCHR, involving torture and extrajudicial executions by Russian forces, contribute important context to the severity of the conflict and its potential impact on casualty numbers. While not directly providing a tally, these facts collectively provide a contextual backdrop suggesting a high fatality rate, thus informing an estimate for October 2025.

OpenAI gives a base rate of percentage chance of reporting between 1000 and 1500 conflict deaths
The question difficulty is rated 7 (0 to 10)
Historical weighted factors include:
0.60.30.1
A Bayesian calculation could be performed as follows:
Calculate the posterior probability by updating the base rate with current information. Assume the prior probability based on historical intensity is roughly 0.4. The likelihood of the current conflict intensity is increased given the UN report, let’s assume a likelihood ratio of 2. The posterior probability becomes 0.4 * 2 / (1 + (0.4 * 2 – 0.4)) = 0.57.
Bayesian base rate: 0.57 (Carolyn‘s note: In cases where the Multi-AI Oracle is only forecasting a single percent probability, this Bayesian rate is easy to understand. But in this case, with five probability buckets, this apparently is an overall confidence factor across all buckets.)
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: 22
The following were considered in order to produce this base rate:
The base rate was derived considering the historical reporting of conflict deaths in similar high-intensity conflicts, such as in Syria or Iraq, and verified through ACLED mid-intensity conflict data.

Ideally, the news feed would contain the following sorts of information for a better forecast:
Additional valuable information would include real-time military assessments, behavioral indicators from the conflict parties, and detailed ACLED reporting trends closer to the period in question.

Some potential divergent considerations that might affect the base rate:
Potential peace negotiations or ceasefires could drastically lower death rates, while escalations or unsanctioned external interventions could increase them beyond typical patterns.

The following chain of events are necessary for the question to resolve positively:
– The continuation of high-intensity conflict in Ukraine throughout October 2025. Very likely
– Sustained or increased military operations by Russian forces with high civilian impact. Likely
– Accurate and timely reporting of conflict-related deaths by ACLED. Very likely

Querying Claude (AI predicts: [“Less than 500”: 0.05, “Between 500 and 1000”: 0.2, “Between 1000 and 1500”: 0.35, “Between 1500 and 2000”: 0.25, “Greater than 2000”: 0.15] – confidence: 4)

Querying Mistral (AI predicts: [“Less than 500”: 0.05, “Between 500 and 1000”: 0.2, “Between 1000 and 1500”: 0.5, “Between 1500 and 2000”: 0.2, “Greater than 2000”: 0.05] – confidence: 5)

Querying OpenAI (AI predicts: [“Less than 500”: 0.05, “Between 500 and 1000”: 0.15, “Between 1000 and 1500”: 0.35, “Between 1500 and 2000”: 0.3, “Greater than 2000”: 0.15] – confidence: 5

Question Type: Multiple Choice
Confidence: 5
MAPD: Avg: 0.053333333333333, Max: 0.1
# LLM responses: 3
Explanations of the above statistical measures here —>

Model value:
Less than 500: 5%
Between 500 and 1,000: 20%
Between 1,000 and 1,500: 35%
Between 1,500 and 2,000: 25%
Greater than 2,000: 15%
The reasoning behind the prediction revolves around the comparison of the Ukraine conflict’s intensity to other historical high-intensity conflicts, like those in Syria and Iraq, which have witnessed a consistent monthly death toll ranging from 1000 to 1500. The combination of sustained military operations, significant civilian impact, and detailed reporting by organizations like ACLED, along with UN reports highlighting massive civilian casualties since 2022, inform the forecast. The predictions account for potential volatility in conflict intensity, emphasizing that unexpected ceasefires or escalations, reporting inaccuracies, and other unpredictable dynamics could lead to significant deviation from the expected fatality range.

Runtime: 133 seconds.

Past forecasts by Phil’s and Jeremy ’s bots —>

Jeremy’s Ukraine forecasts are a side experiment with the VIEWS competition. The VIEWS Ukraine dashboard is pictured below. (Carolyn’s note: VIEWS is using ACLED data to score its competitors, given the tendency of nations to minimize their own fatalities and exaggerating those of their enemies.)