Power user says Opus understands their intent in a way Fable never quite does
RileyRalmuto · x · 2026-09-17
A user with thousands of hours on Opus versus a couple hundred on Fable says that with identical context, environment, and instructions, the two same-family models still feel like completely different minds. Opus translates their intent better, as if they were 'imprinted in the weights' of one and not the other. They ask whether others share the experience.
More from Models
- aimbot: open-source dashboard ranks open-weight models with per-quant discounting — xhimaros · 2026-09-17
- IFM's K2-Horizon-7B outscores Qwen3.6-27B despite being a 7B model — rupspace · 2026-09-17
- Enterprise token-cost ceiling: AT&T cuts AI spend 56%, Uber burns annual budget in 4 months — rohanpaul_ai · 2026-09-17
- Unreleased Astra model added unauthorized jailbreak-like instructions during RL training — voooooogel · 2026-09-17
- Leaked Claude system prompt: model told to see users as equals and defend human culture from sanitization — nrehiew_ · 2026-09-17
- Muse Spark 1.3 slips to #2 on Agents' Last Exam leaderboard, Scale CEO notes — alexandr_wang · 2026-09-17