Reviewer: Claude Opus 5.5's real win is taste, not benchmarks — usage far lower than expected
Hesamation · x · 2026-09-27
- Hesamation shares impressions of using Opus back in Claude Code: the big win isn't benchmarks but TASTE — taste in approach and design; the model feels smart, efficient, and genuinely fun to work with.
- Usage: after days of heavy use, consumption is far lower than expected, though he can't tell whether that's Opus or recent Claude Code efficiency gains.
- Compared to older verbose, needy Claude versions, he says Opus 5.5 matches Astra at grinding on a task for hours and suggests lapsed users give it another shot.
More from coding & agent
- Explosion launches Ellf directory: 52 NLP templates plus multi-agent annotation workflow — _inesmontani · 2026-11-11
- Meme: 'Stochastic AI Agent Architecture' Is Just a Markov Chain in Disguise — PrasoonPratham · 2026-11-11
- OpenCode adds Gemini 4 Carbon and Claude Fable 5.2 support — dean_rie · 2026-11-11
- OpenClaw v2026.11.3 patch fixes cert verification and credential exposure across 56 PRs — dean_rie · 2026-11-11
- Fable 5.2 captured 1 in 4 Claude replies on day one, then growth stalled — dean_rie · 2026-11-11
- QA engineer proposes MCP agent to automate ad postback checks before every app release — Soobhee_Chukwutosin · 2026-11-11