Blast Radius
2026-08-07 • Artificial Intelligence
Artificial Intelligence
AI summaryⓘ
The authors introduce Blast Radius, a system that helps language models manage memory more efficiently when working on tasks, reducing wasted tokens. It predicts how far a prompt will need to access past context or code and can temporarily remove unused parts without losing data, using methods called NECROPHORESIS and Recurring Dead Matter to handle repeated or obsolete information. Tested on several models, Blast Radius lowered token use by up to 26% while keeping all changes reversible. This approach aims to make AI coding tools more sustainable and easier to reuse.
agentic codingtoken consumptioncontext managementNECROPHORESISRecurring Dead Mattercontext evictiontoken overflowOpenAI modelscontext entropyreversible memory
Authors
MY Pitsane, Hope Mogale
Abstract
Agentic coding faces growing problems of affordability and wasted tokens. We introduce Blast Radius, a predictive memory management layer that estimates an incoming prompt's reach through coupled context and code channels. NECROPHORESIS enables reversible eviction by archiving dead context verbatim, while Recurring Dead Matter (RDM) identifies and buries repeatedly occurring transcripts. We formulate reversible context eviction over a Polish context space, providing a measurable foundation for retention, recurrence, and eviction while connecting context entropy to resurrection probability. Across seven OpenAI models, Blast Radius reduced token consumption by 17-26%, achieved the lowest overflow rate among tested policies, and remained byte exact reversible. Of 450 buried bodies, 378 were recurring dead matter and zero were recalled. Blast Radius operates beneath HCRC, determining which records to bury and how far an incoming prompt may reach into the codebase. This work contributes to the broader goal of Algosophy: making large language models and agentic coding more reusable and sustainable.