#coding-agents
- Mistral releases Medium 3.5 — 128B dense, 256k context, open weights Mistral models-llm
- Mistral Launches Medium 3.5 Open-Weight Flagship and Remote Coding Agents in Vibe Mistral AI models-llm
- Z.ai ships GLM-5.3: frontier coding via post-training only, emergent cyber capabilities Z.ai (Zhipu AI) models-llm
- Dockerless: Environment-Free Program Verifier for Coding Agents ByteDance research
- GPT-5.6 Sol Ultra Arrives in Codex with Subagent-Powered Ultra Mode OpenAI tools
- Yandex launches "75/75/75" program to push AI-native software development Yandex industry
- Ouroboros: A Self-Developing Coding Agent That Evolves Its Own Harness Through Reviewed Commits research
- Claude Code v2.1.200: Manual Permission Mode Becomes Default Anthropic tools
- The Verification Horizon: No Single Reward Function Works for Coding Agents at Scale Qwen (Alibaba) research
- GitHub Copilot CLI Drops PAT Requirement in Actions; Agent Session Streaming in Preview GitHub tools
- OpenCode (SST) v1.17.13: MCP Resource Template Tools and Reasoning-Mode Enforcement SST tools
- OpenAI Codex CLI 0.142.5: Trace-Log Privacy Fix OpenAI tools