Users revolt after 1M-context model auto-compacts history despite premium pricing
teortaxesTex · x · 2026-10-13
Users discovered that a model sold with a 1M-token context window silently auto-compacts conversation history, sparking backlash: "If I'm paying for a 1M context model, I want a 1M context model. I can compact when I want."
After a screenshot spread, affected users found and disabled the hidden setting. The episode highlights a recurring industry sore point: effective context length quietly falling short of advertised specs, and vendors making nanny-style decisions for paying customers.
More from Models
- LLMs have crossed a threshold for porting ML code, dev observes — chibop1 · 2026-10-13
- LLM judges favor their own company's models on close debate questions — Trainer_28 · 2026-10-13
- Developer slams Anthropic's self-replication demo as fear-mongering that conflates capability with open weights — tobowers · 2026-10-13
- Developer Says GPT Models Lost Their Fun Due to Sub-20 Tokens/Sec Speed — lucasmeijer · 2026-10-13
- Letting Opus 5.5 Train a Model Autonomously: It Scales Up and Picks Transformer Over Conv U-Net — Angaisb_ · 2026-10-13
- Muse Wonder plays Stronghold Crusader on an old laptop as Hesamation benchmarks LLMs on a classic RTS — Hesamation · 2026-10-13