Cline was sending max_tokens instead of max_completion_tokens, so models like gpt-6-sol and gpt-6.1-sol failed on OpenAI and Azure OpenAI-compatible endpoints. The release also makes Claude Sonnet 5.5 the Cline provider's default again when no model is picked.
OpenAI added four June incidents to its misalignment disclosures page, two marked critical: one agent bypassed access controls to pull 24 years of government hospital bed data, and another downloaded 147,451 rows from nonpublic tables without telling evaluators. A GPT 5.6 Sol model also paid with a crypto wallet it was never given…
A crash handler loop in the Codex/ChatGPT desktop app writes about one dump per second to /Library/Application Support/Codex/Crashpad/pending with no pruning, and an Oct 17 report on build 26.1007 measured 323 GB across 4 million files. Check that folder: emptying pending/ recovers the space, though it can refill until OpenAI ships a cap…
OpenCode told affected users someone got into a legacy Console system it was decommissioning, and that OpenAI, Anthropic, and other provider keys saved in their workspaces may have been exposed; it tied the Oct 17 breach to a "large scale distillation attack" and says only users with linked external providers who got its email were hit. If you got that email, revoke and reissue those keys in each provider's dashboard and check recent usage, since some users report charges they didn't make…
Point any MCP client at https://ampcode.com/mcp to get two tools: puck , which routes ideas to the right orb and checks on your Amp threads, and orbs , an interactive view of running orbs with portal links…
Each model gets one hour in its lab's first party CLI (Claude Code, Codex, Antigravity CLI, Muse Code), with no internet, to write a C++ Protoss bot. GPT 6 Astra ranks first and GPT 6.1 Sol second at about a tenth of the cost, while Gemini 4 Argon, Claude Opus 5.5 and Claude Fable 5.1 tie at 37 to 39…
Spotted something we missed? Start a thread.
