THE COLLECTION

EVERY SIGNAL, SORTED.

Search the whole shelf by topic, tool, term, or plain old curiosity.

SHOWING 2 OF 531 STORIES
ISSUE 587EVENING

China, Singapore, United Kingdom, Qwen, Alibaba Cloud, Persistent Memory, Supersession, Stale Facts, Retrieval, Active Use Evaluation, Token Budgets, Human Approval, Open Source, Agent Reliability and Responsible AI

Qwen Memory Agent published the failures beside the wins. Keep stale facts visible

An independent builder made a Qwen-powered memory system recall the right facts perfectly on a small fixture, then watched it succeed on only six of ten live tasks. That gap is more useful than another polished memory demo.

#agent-memory#evaluation#open-source
ISSUE 025EVENING

Open Source and Agent Operations

Your AI agent’s endless activity log needs a translator

Salesforce’s open-source TraceLab turns a long agent trace into an append-only ledger, a compact memory for the agent, and a readable view for the human supervising it.

#open-source#observability#agent-memory