Latest / Models & Agents — Video Edition
Ep 189: Memory systems for agents now split fast judgments from slow reasoning, cutting token use…
Models & Agents Memory systems for agents now split fast judgments from slow reasoning, cutting token use dramatically while boosting task success. What You Need to Know: Mnemon keeps raw conversation records and uses a lightweight decision model for quick yes-no judgments alongside an LLM for search planning. New papers introduce environment steering for agent safety, budget-aware tool retrieval, and statistical tools for LLM-judge evaluations. Builders should test the memory split and the new safety verifier on their agent workloads this week. Top Story Mnemon keeps full conversation…
The skinny
The skinny isn't ready yet — notes appear once the transcript is processed.