US judge approved $1.5B settlement with authors over pirated books used to train Claude

Traders bet Claude Opus 4.8 launch imminent within days based on options market activity

Max plan users report 3-4x faster limit exhaustion on Claude Code, with a single continue message consuming ~3% of the 5-hour limit

Launched the Claude Certified Associate — Foundations (CCAO-F) certification program

Anthropic ARR hit $69B.

Released the Kotlin Benchmark for AI coding agents on real-world Kotlin tasks

Published J-space paper demonstrating causal reasoning control and model detection of interventions

JetBrains ran a proper A/B benchmark on the Caveman skill for Claude Code, finding 8.5% token savings instead of the claimed 65%.

Open-sourced Mellum2, a 12B MoE model with 2.5B active parameters for code and reasoning