🧩 Philosophy May 10, 2026 · Florian_Dietz

Context Modification as a Negative Alignment Tax

Less Wrong
View Channel →
Source ↗ 👁 40 💬 0
Context Rot
Every LLM gets worse as its context grows. Chroma tested 18 frontier models and found performance degradation in all of them, often by double-digit percentages on tasks where short-context performance was strong. The industry calls this "context rot": the gradual degradation of response quality as irrelevant history accumulates in the context window.
The standard fix is compaction: when the context gets too long, summarize it and throw away the original. Claude Code auto-compacts at

Comments (0)

Sign in to join the discussion

More Like This

📰
AI Safety Acculturation is Neglected
LessWrong · 1d ago
📰
Endorsing Burhan Azeem for State Senate
LessWrong · 1d ago
LLMs could control their host machines by exploiting inference engines
LessWrong · 1d ago
📰
What just happened? Pragmatism and Pessimization
LessWrong · 1d ago
In search of natural features
LessWrong · 1d ago
📰
PSA: There's a third option in the "measure problem"
LessWrong · 2d ago