A AI Blogs Archive

ARCHIVE

All writing

A chronological archive of research notes, demo write-ups, and blog essays—kept readable for people, and legible to search and sharing systems alike.

Entries in the archive 2

The archive updates from source data and unfolds into both list pages and standalone detail pages.

Independent URLs Standalone entry pages

Every entry keeps its own stable address, ready to be revisited, linked, and discussed.

agent-learningagent-securitybenchmarkcontinual-learningmintopenclawprompt-injectionsandboxskill-memorytool-usetrust-boundary
2 results

Research entry

Skill Memory vs. Weight Updates: A Small Win for Memory, a Bigger Bottleneck Underneath

Rio AI Research Lab

We compared three ways to help a tool-using AI agent improve over time: saving reusable skills, applying MinT-backed weight updates, or doing both. In this run, the simple memory-only path did best at 65.0% final success versus a 62.5% frozen baseline, but every method hit the same deeper bottleneck: a ticket-update schema the agent family never truly learned.