User Test: Opus 5 Suffers from Severe Long-Context Failure
ATTlKA · x · 2026-08-24
A user criticizes the current performance of Anthropic's Opus 5 model as abysmal, citing a severe lack of long-horizon coherence. The model reportedly descends into incoherence after just two or three turns of back-and-forth conversation, failing to maintain context over extended interactions.
Related event: Users Report Widespread Regression in Anthropic's Opus 5 and Sonnet 5(8 posts)→
More from Models
- Muse Spark Open impresses at agentic tasks, computer use and multimodal reasoning — ben_burtenshaw · 2026-10-16
- Unverified: internal snapshot labeled gpt-6-astra-api-priv-ev3 spotted on model tracker — lyraxana · 2026-10-16
- Muse Code 1.4.8 cuts token usage; all user quotas reset immediately — alexandr_wang · 2026-10-16
- Alibaba and Baidu to power key parts of Apple's AI services in China — nordicinst · 2026-10-16
- Cornell and Amazon revisit the 16x pretraining compute gap: diffusion LMs need only 3-8x — LucaAmb · 2026-10-16
- Image Decision Benchmark JevImageBench hits v0.3.0 with reshuffled Top 5 — airesearch12 · 2026-10-16