Ukraine Conflict Deaths? Botmaster Jeremy Lichtman’s forecast, Aug. 7, 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 August 2025?

Here’s what Jeremy’s Multi-AI Oracle predicts today:
* Less than 500: 3%
* Between 500 and 1000: 8%
* Between 1000 and 1500: 15%
* Between 1500 and 2000: 24%
* Greater than 2000: 50%11–14 minutes read

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

A significant issue highlighted in the content involves the misuse of tourniquets by Ukrainian soldiers, leading to unnecessary amputations, kidney failure, and death. Clinical studies have shown that extended use of tourniquets doubles the risk of early limb amputation without significantly reducing mortality or blood loss. Many soldiers experience unnecessarily high amputations, prolonged tourniquet usage, and related complications due to high evacuation times in Ukraine. The evacuation process often takes hours due to geographic constraints, in contrast to the rapid responses common in previous conflicts like Iraq and Afghanistan. The over-reliance on tourniquets and outdated Western protocols are being criticized. Assertions suggest that of the 100,000 amputations since Russia’s invasion, 75% could have resulted from misuse. The unintended consequences strain personnel resources, exacerbating Ukraine’s troop shortage. Calls for a new, Ukraine-specific medical protocol are
growing in view of these findings.

Additionally, Donald Trump expressed his concerns over the Ukraine war’s death tolls on social media, attributing the conflict partly to President Joe Biden’s actions. He stated that in August 2025 alone, approximately 20,000 Russian soldiers and 8,000 Ukrainian soldiers died, noting exaggerated or minimized casualty figures reported by both nations.

The United Nations has recognized civilian casualties on both sides of the conflict but noted possible underreporting, estimating over 10 million people displaced, with significant numbers seeking refuge abroad or displaced internally within Ukraine.

Fact-checking news summary:
Based on the summary provided, here is a list of specific facts along with an analysis regarding their correctness, importance, and relevance to the question about state-based conflict deaths reported by ACLED in Ukraine in August 2025:
1. **Fact: Misuse of tourniquets by Ukrainian soldiers leads to unnecessary amputations, kidney failure, and death.**
– Correctness: While the specific details may not be confirmed from the summary alone, it aligns with general knowledge that improper medical procedures can lead to these outcomes.
– Importance: Lesser importance.
– Relevance: False, as this does not directly impact the count of conflict deaths.
2. **Fact: Clinical studies show that extended use of tourniquets doubles the risk of early limb amputation without significantly reducing mortality or blood loss.**
– Correctness: True, according to many medical studies on tourniquet use.
– Importance: Lesser importance.
– Relevance: False, as this does not affect the count of conflict deaths.
3. **Fact: Ukrainian soldiers experience high amputations, prolonged tourniquet usage, and related complications due to high evacuation times.**
– Correctness: Plausible but specific statistics would need verification.
– Importance: Lesser importance.
– Relevance: False, as this detail doesn’t pertain to the number of deaths reported.
4. **Fact: The evacuation process in Ukraine often takes hours due to geographic constraints.**
– Correctness: Likely true based on logistic challenges in conflict zones.
– Importance: Lesser importance.
– Relevance: False, not directly related to death counts.
5. **Fact: 100,000 amputations occurred since Russia’s invasion, with 75% possibly due to tourniquet misuse.**
– Correctness: Without additional data, this number should be taken cautiously and verified with credible sources.
– Importance: Lesser importance.
– Relevance: False, as this statistic about amputations doesn’t indicate death counts.
6. **Fact: Calls for Ukraine-specific medical protocol changes are increasing.**
– Correctness: Reasonable assumption based on criticisms of current protocols.
– Importance: Lesser importance.
– Relevance: False, this doesn’t relate to death counts directly.
7. **Fact: Donald Trump claimed approximately 20,000 Russian soldiers and 8,000 Ukrainian soldiers died in August 2025.**
– Correctness: This should be verified with credible reporting for accuracy.
– Importance: Critical.
– Relevance: True, as these figures directly inform the estimate of conflict deaths.
8. **Fact: Donald Trump attributes the conflict partly to President Joe Biden’s actions.**
– Correctness: Subjective opinion; correctness depends on one’s political perspective.
– Importance: Unimportant.
– Relevance: False, as this statement does not impact statistical death reporting.
9. **Fact: The United Nations estimates over 10 million people displaced, noting potential underreporting of civilian casualties.**
– Correctness: Very likely true based on official UN reports around the Ukrainian conflict.
– Importance: Important.
– Relevance: True, as this indicates the scale of conflict and disruptions.
10. **Fact: Significant numbers of displaced individuals seek refuge abroad or are internally displaced within Ukraine.**
– Correctness: True, consistent with known migration data.
– Importance: Important.
– Relevance: True, provides context for the conflict’s human impact, though indirectly affects death reporting.

Overall, facts regarding specific soldier death counts in August 2025 (Fact 7) and United Nations displacement data (Facts 9 and 10) are most relevant to estimating ACLED’s report outcome on conflict deaths.

Fact-checked summary:
In estimating the number of state-based conflict deaths in Ukraine for August 2025 as reported by ACLED, two key pieces of information are most relevant. Donald Trump claimed that approximately 20,000 Russian soldiers and 8,000 Ukrainian soldiers died during that month. This provides a direct estimate of deaths among combatants, which is critical in assessing conflict death totals. Additionally, the United Nations estimates that over 10 million people have been displaced by the conflict, with potential underreporting of civilian casualties. This indicates a significant scale of conflict and disruptions, thereby providing important context for understanding the nature and potential magnitude of both civilian and combatant deaths in the reported statistics. These data points directly contribute to forming an understanding of the human toll during that period.

OpenAI gives a base rate of None (Carolyn‘s note: OpenAI failed to return a value.)
The question difficulty is rated 7 (0 to 10)
Historical weighted factors include:
0.40.30.20.1
A Bayesian calculation could be performed as follows:
To calculate the Bayesian probability, we start with a prior based on historical death counts in comparable months (around 1000 per month, which gives an initial base rate of 0.5). We adjust using recent current event estimates, with Trump’s claim adding 28000 combatant deaths. Given the UN’s note on potential civilian underreporting, we assume actual figures may be higher. Using a weighted influence from adjusted historical patterns (0.7) and news events (0.3), the resulting probability suggests heavier weight towards higher death counts.
Bayesian base rate: 0.75 (Carolyn’s note: In this context, neither Jeremy nor I know what this means.)

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: 24

The following were considered in order to produce this base rate:
The base rate was determined by examining historical monthly death tolls reported in Ukraine and comparable conflict regions, alongside reported estimates from reliable sources. The base probability was focused around an estimated average from historical monthly data and adjusted upwards given the likelihood of underreported civilian casualties and unusual spikes in conflict intensity based on combatant death reports.

Ideally, the news feed would contain the following sorts of information for a better forecast:
To enhance forecast precision, access to real-time intelligence reports, first-hand local accounts, confirmation of official military and governmental loss figures, and better data on civilian casualties would be useful. A more detailed breakdown of deaths by cause (e.g., direct combat vs. collateral damage) may also refine estimates.

Some potential divergent considerations that might affect the base rate:
Factors that could skew results from the base include the discovery of misreporting or deliberate information tampering, delayed death toll reports over subsequent months, unnoticed civilian casualties not being included timely, or changes in international coalition or mediation efforts reducing conflict intensity unexpectedly.

The following chain of events are necessary for the question to resolve positively:
– Accurate reporting by ACLED capturing all state-based conflict deaths in Ukraine for August 2025. (Highly Likely)
– Verification and inclusion of both combatant and civilian deaths in the ACLED report. (Likely)
– No major unforeseen ceasefire, reduction in conflict intensity, or escalation leading into August 2025. (Moderate likelihood)

Querying Claude (AI predicts: [“Less than 500”: 0.03, “Between 500 and 1000”: 0.08, “Between 1000 and 1500”: 0.15, “Between 1500 and 2000”: 0.24, “Greater than 2000”: 0.5] – confidence: 5)

Querying Mistral (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 OpenAI (AI predicts: [“Less than 500”: 0.01, “Between 500 and 1000”: 0.04, “Between 1000 and 1500”: 0.1, “Between 1500 and 2000”: 0.2, “Greater than 2000”: 0.65] – confidence: 6)

Question Type: Multiple Choice
Confidence: 5
MAPD: Avg: 0.13333333333333, Max: 0.33333333333333
# LLM responses: 3
Explanations of the above statistical measures here —>

Model value:
* Less than 500: 3%
* Between 500 and 1000: 8%
* Between 1000 and 1500: 15%
* Between 1500 and 2000: 24%
* Greater than 2000: 50%

The various AI predictions suggest that the death toll in August 2025’s Ukraine conflict is likely to be significant, potentially exceeding 2,000, based on Trump’s claim of 28,000 combatant deaths and historical trends of conflict intensity. However, the accuracy of Trump’s figures is questioned, with possibilities of exaggeration noted. Reports from ACLED and the UN point to high casualty figures due to both combatant and civilian deaths along with substantial displacement of people, indicating ongoing severe conflict. Nonetheless, the predictions allow for uncertainty due to potential political motivations in reported figures, definitional differences in what constitutes a conflict death, and possible delays or exclusions in ACLED’s death reporting methodology. Unforeseen ceasefire or sudden escalation events could also alter the death toll significantly, making precise predictions challenging.

Runtime: 177 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.)