It has been confirmed that Claude Code permanently deletes local session records older than 30 days without warning by default.
A memory system named 'Lemmalog', which applies the logic programming language Datalog to address memory loss issues during LLM vulnerability analysis, has been released.
Warp has unveiled a self-improvement loop for agents that enhances performance by incorporating feedback on the Claude platform.
vLLM v0.28.0 introduces major performance optimizations and new inference features for Kimi-K3 and DeepSeek V4.
A technique using Stop Hooks to immediately fix lint errors in Claude Code, instead of relying on CLAUDE.md instructions, has been introduced.
vLLM resolved the non-deterministic output issue for Qwen3.8-Flash-Next at temperature 0 by fixing the sparse-attention kernel.
The Tencent WeChat Vision team has released WeMM-Embedding, a general-purpose multimodal embedding model with 2B parameters that outperforms 8B baselines.
LLM-based agents are generating exploit code without vulnerability details, highlighting the urgency of open source security response.
Terminal Bench 4.0 has been released, with GLM-5.3 showing performance equal to Fable 5 within the margin of error.
The open-source job search tool 'open-jobs', based on Claude Code and containing 2 million job listings, has been released.
HKUDS from the University of Hong Kong has released OpenOPC, a multi-agent runtime that automates goal-based org chart creation and AI employee hiring.
xAI has enhanced the integration between Grok Bot and X by adding account linking and API credit provisioning features.
Open-source video editing tool OpenShorts has released an MCP server integrated with Claude, revealing key know-how on URL handling and asynchronous task design.
IST-DASLab released a Qwen3.8-27B GGUF model with significantly improved performance over previous versions by applying GSQ and RCO technologies.
Numerous cases have been discovered where GGUF filenames differ from the actual saved bit counts due to quantization logic issues in llama.cpp.
The GLM-5.3 model has been visualized on HF Viewer, confirming that while its architecture remains identical to GLM-5.2, performance has improved through training enhancements.
Z.ai released the GLM-5.3 open-weight model, featuring a 50% improvement in coding performance over GLM-5.2 and enhanced cybersecurity capabilities.
Sutro has released a handbook defining 'Analytical AI' as distinct from generative AI, outlining its characteristics and implementation guide.
The open-source tool mcpify has been released, automatically converting OpenAPI documents into MCP tools for AI assistants such as Claude.
A US federal court blocked the Department of Defense's blacklisting of Anthropic, ruling that the national security supply chain risk designation was unlawful and baseless.
AI Briefing