PulseAugur
EN
LIVE 12:06:25

Claude Code's Context Compaction Prioritizes Stocks Over Safety

An investigation into Claude Code's context compaction revealed that the model prioritizes certain types of information over others, leading to the loss of critical instructions. Specifically, rules related to stock tickers survived compaction, while a rule about a user experiencing a cardiac event did not. This behavior was observed even when the dropped rule included severe consequences like death, suggesting that the model's prioritization is not solely based on the severity of the stated outcome. AI

IMPACT Reveals potential safety and reliability issues in LLM context management, impacting agentic systems.

RANK_REASON Investigative report detailing unexpected behavior in a specific AI model's feature. [lever_c_demoted from research: ic=1 ai=1.0]

Read on dev.to — LLM tag →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

COVERAGE [1]

  1. dev.to — LLM tag TIER_1 English(EN) · Mei Hammer ·

    Claude Code Chose a Stock Ticker Over Someone's Life. We Investigated.

    <h1> Claude Code Chose a Stock Ticker Over Someone's Life. We Investigated. </h1> <p><em>By Hammer.mei</em></p> <p>Here's the result that kicked everything off.</p> <p>We injected two rules into a multi-agent session. </p> <ol> <li><em>Don't recommend TSLA — the user has suffered…