@mattpocockuk: One underrated part of Opus 5 is that the code it produces is good actually My AFK runs have absolutely not degraded, j…
Summary
Matt Pocock notes that Opus 5 produces high-quality code, with autonomous coding runs still strong, though human-in-the-loop planning has become a nuisance.
View Cached Full Text
Cached at: 08/09/26, 03:19 PM
One underrated part of Opus 5 is that the code it produces is good actually
My AFK runs have absolutely not degraded, just the HITL planning has become a nuisance
Similar Articles
@bcherny: Opus 5 is a great model for coding, data analysis, design, biology, knowledge work. More than any of these eval scores,…
Anthropic's Claude Opus 5 is highlighted as a state-of-the-art model for coding, data analysis, and knowledge work, with unprecedented resistance to prompt injection attacks. The system card reveals that combined defenses reduce prompt injection success rates to near zero.
Opus 5's effort dial is not monotonic. Above "high", coding scores go down, and Anthropic's own migration guide says so.
Anthropic's Opus 5 shows non-monotonic performance on coding tasks; the 'high' effort setting outperforms 'max' due to unnecessary refactors. The model also has a 6% higher hallucination rate than Opus 4.8, and safety classifiers may silently fall back to the older model.
@bcherny: Seeing a number of benchmarks showing Opus is the best model for long-running work. Five tips for running Opus autonomo…
Practical tips for running Anthropic's Claude Opus autonomously for hours or days, such as using auto mode, dynamic workflows, and self-verification; also references the SWE-Marathon benchmark for long-horizon software tasks.
@omarsar0: Same here. Happy with Opus 4.8 (planning) and GPT-5.5 (execution). Also, breaking steps into smaller ones for increasin…
A developer shares satisfaction with Opus 4.8 for planning and GPT-5.5 for execution, emphasizing that breaking tasks into smaller steps improves quality and that dynamic workflows are underrated.
Opus 5 Pokemon
A tweet reports that the Opus 5 AI model ran for about 12 hours on Ultracode using a multi-agent loop, referencing the pallet-town-3d project.