CLAUDE-OPUS-46
30 days · UTC
Synchronizing with global intelligence nodes...
Claude Opus 4.6 pricing isn’t one thing: seats vs tokens, very different bills
Anthropic splits Claude Opus 4.6 access between seat-based app plans and token-metered API usage, which leads to very different costs in practice. [T...
Claude Code after Opus 4.6: new defaults, noisy regressions, npm change, and a brief outage
Claude Code flipped key defaults with Opus 4.6, prompting mixed results as install paths changed and Claude had a brief outage.
Cursor IDE users report severe slowdowns and regressions tied to recent builds and usage caps
Multiple Cursor IDE bug reports point to performance degradation, editor breakages, and throttling-like behavior near plan limits.
Cheaper coding LLMs and subagent stacks are here—time to re-architect your model routing
Production-ready, cheaper models plus subagent patterns are shifting AI economics for coding and document workflows. Z.ai’s new GLM-5.1 posts a 45.3 ...
Top LLMs split on tiers and naming: what that means for cost, routing, and long jobs
Vendors now expose high‑end LLMs with different tiers and names, which changes how you budget, route jobs, and handle long or tool‑heavy tasks. A dee...
Cursor Composer 2 ships strong and cheap, then admits Kimi K2.5 base
Cursor released Composer 2, then acknowledged it sits on Kimi K2.5, raising provenance questions despite strong performance and low prices. Composer ...
Claude Code adds Auto Mode and scheduling, with security guardrails in preview
Anthropic is adding an Auto Mode to Claude Code that reduces permission prompts while introducing admin safeguards, higher token costs, and new schedu...
GPT-5.4 lands: long context, native computer use, and coding gains
OpenAI’s GPT-5.4 is rolling out with stronger coding, long‑context reasoning, and native computer‑use, pushing teams to revisit model selection, guard...
Benchmarks Are Breaking: Evaluate LLMs in Your Harness, Not Theirs
LLM benchmark scores are failing under real-world conditions, so choose and tune models by testing them in your own harness with controlled tools and ...
MiniMax-M2.5 launches with SOTA coding claims; verify SWE-bench results
MiniMax launched MiniMax-M2.5, a fast, low-cost coding and agentic model, but teams should validate its headline SWE-bench gains with internal tests g...
Claude Code v2.1.68 sets Opus 4.6 to medium by default and reintroduces one-turn "ultrathink"
Claude Code v2.1.68 changes default model behavior to Opus 4.6 at medium effort, re-enables a one-turn high-effort "ultrathink" switch, and migrates a...
Windsurf ships new models, Linux ARM64, and enterprise hooks
Windsurf rolled out new frontier coding models, full Linux ARM64 support, and enterprise-grade Cascade Hooks while community feedback spotlights its t...
Opus 4.6 Agent Teams vs GPT-5.3 Codex: multi‑agent coding arrives for real SDLC work
Anthropic's Claude Opus 4.6 brings multi-agent "Agent Teams" and a 1M-token context while OpenAI's GPT-5.3-Codex counters with faster, stronger agenti...