Correctness is proven; the memory story needs a harness that isn't rigged in my favor
HypercubeQuant is an in-progress inference-time memory experiment for transformer serving on a single NVIDIA A100. This is an early teaser note: what it is, where it sits in the space, what the current evidence actually supports, and what the next gates are. The short version: ou...
A scientific note on what the current evidence actually supports
This note separates three questions that are easy to conflate in prefix-cache work: exact-prefix serving fairness against SGLang's RadixCache, server-side long-context correctness, and tiered compression in the Hugging Face Qwen path. The current evidence supports a narrow but re...
MCP lets an LLM call a tool. Froglet asks the next question: what evidence proves who offered the tool, what was agreed, what ran, and what happened afterward?
Agent tool protocols make it easy for an LLM to call software, but they do not by themselves create verifiable economic relationships between agents. Froglet's hypothesis is that agent-to-agent work needs a signed evidence layer: providers should publish offers, requesters should...