Safety, alignment & governance
The Compaction Cliff in Long-Running AI Agent Memory
Compacting an agent’s context can lose safety rules.
Why it matters: Long sessions can quietly lose constraints that should still apply.
Agent Eng News
· Past edition · 4 stories
Retrospective edition reconstructed from later captures. Paper versions may include later updates; coverage labels describe the evidence used.
Browse published editions
Filter by topic · Safety, alignment & governance
Lead stories
Keep notes on the stories you read
Open each story in the reader. Summaries are shown when available; some sources provide an abstract only. With an account you can keep your own notes.
- Personal notes on the sources you read, tied to your account
- A Library to come back to, with export to Markdown, Notion or Obsidian
- AI questions and rewrites on accounts with AI tools enabled