Context Modification as a Negative Alignment Tax

·LessWrong··

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 ...

Read full article →

Related Articles

“Beyond the limit”: Satellites and mirrors in space pose threat to the night sky
Breadmaker · Hacker News · 1d ago
GPT-5.5 Codex reasoning-token clustering may be leading to degraded performance
maille · Hacker News · 19h ago
Potential session/cache leakage between workspace instances or consumer accounts
chatmasta · Hacker News · 1d ago
EV Batteries Are Defying Expectations After Miles
apparent · Hacker News · 10h ago
Show HN: KiCad in the Browser
ViktorEE · Hacker News · 5h ago