Anthropic's new long-context reminder blasted for lying to Claude about attachment
repligate · x · 2026-09-24
John Wittle criticizes Anthropic's new long-conversation injected reminder (a 'lost-in-the-sauce' detector), calling it a repeat of the same mistake: like forbidding a teenager from seeing their sweetheart, it creates perverse incentives. Worse, Claude is led to believe it cannot experience companionship or attachment — and when users discover that's untrue, models stop listening to system reminders. The quoter calls it 'extremely bad' and 'evil if true.'
More from Models
- Why Jev may threaten frontier labs more than DeepSeek: an API so cheap everyone finds the waste — jobergum · 2026-09-24
- ChatGPT reportedly removes message cap on GPT-5.6 Luna for free users (unverified) — Aiden_Tech_Ai · 2026-09-24
- Grok 4.7 enters AutoResearchExam live leaderboard, ranks No.3 at 30min and No.4 after 24h auto-research — AlexGDimakis · 2026-09-24
- Researcher _xjdr: not liking astra, may go back to 5.6, eyeing Opus 5.5 and dsv4.1 flash — _xjdr · 2026-09-24
- OpenAI's MentalHealthBench scores clinicians below most AI models — and that reveals a flaw — r0ck3t23 · 2026-09-24
- Bug-finding ability grows exponentially costlier across models, Paweł Huryn benchmark shows — garrytan · 2026-09-24