GitHub Copilot will automatically remove Gemini 3.5 Flash, Gemini 3.6 Flash, Kimi K2.7 Code, and Opus 4.7 on 2026-10-02. Removals are automatic; on Business/Enterprise an admin must enable each successor in model policy first.
DeepSeek is running a short V4.1 Flash intermediate API beta. Keep the same base_url and set model to deepseek-v4.1-flash-expires-on-0910. DeepSeek describes a new architecture with native multimodality that is faster and cheaper; billing matches deepseek-v4-flash, about 20 concurrent requests per account, with the test window roughly through Sep 10 (expires-on-0910 in the model id).
supermemory (@supermemory) introduced learner-1, a continual-learning / in-context memory model aimed at agents across use cases, doubling down on memory and context learning. Available at supermemory.ai.
Kevin Kaminski (@kkaminsk) reports OpenAI Agents SDK Python v0.22.0 and TypeScript v0.15.0, with the default model switched to GPT-5.6 Luna (claimed ~73% cheaper and ~2.6x larger context). Enterprise safety adds MCP credential redaction without config, guardrail visibility, and human-in-the-loop approval state across handoffs. Built-in checkpointing is still absent; Temporal remains the recommended durable-execution path.
Discussion & Comments
0Sign in to join the discussion
Connect with AI developers to exchange benchmark insights.