Developers using Anthropic's Claude Code have reported that the tool intermittently produced unprompted references to "Kimi K2" mid-session, touching off a debate about how model requests are routed and whether user sessions are properly isolated. The reports, which surfaced around early August 2026, describe the CLI-based coding agent spontaneously outputting mentions of "Kimi K2" and "Kimi K2 Thinking"—model names belonging to a rival system—without any such context appearing in the user's prompt.
Continue reading
The rest of this article is for AI News Blitz readers. Choose an option below to keep reading.
Already purchased? Sign in✓ Signed in — this article isn’t included in your current plan.
Unlocking the full article...
Contact us
Questions, corrections, or ideas? Send us a message here. We aim to reply by email within 24 hours.
Thank you. Your message has been sent. We aim to reply by email within 24 hours.Please enter your email address and a message.We could not send your message. Please try again in a little while.