MEMA vs. continual learning: three kinds of AI memory
Context windows, explicit MEMA records, and model-internal continual learning solve different problems. Here is the evidence boundary for MEMA, Nested Learning, and a planned HOPE integration.
Blog
Notes from the workshop
Notes on context engineering, AI strategy, and making AI reliable.
The AI literacy obligation: what Swiss companies must now train
Since 2 February 2025, Article 4 of the EU AI Act requires every provider and deployer to ensure a sufficient level of AI literacy among its staff. Swiss firms are in scope the moment their AI touches the EU market. Who the obligation hits, what it demands, and what appropriate measures look like.
Memory an AI agent can inspect
MEMA separates explicit records, retrieval, policy, audit, and integrity checks. Here is what those controls establish—and what they do not—at the current public and internal baselines.
Don't build a company brain. Scope memory small.
Errors in memory don't repeat, they breed. So the size of a memory is the size of its risk. The fix isn't one brain that knows everything; it's many small, isolated memories, each scoped to one cohesive use case.
What an AI agent actually is
Everyone sells agents. Few say what one is. An agent is a model plus four decisions around it: what it sees right now, which rules always apply, what it remembers long-term, and where it runs. The memory part is the hard one.