SkillsSkill 6: Fine-Tune Phi-4-Reasoning-Vision-15B Locally with Unsloth + LoRAUnsloth·medium signal1. Install prerequisites: Python 3.8+, PyTorch with CUDA, `pip install unsloth transformers datasets`SourceSource pageUnsloth↳ Follow the threadShared entity / Stack layerFine-tuning decision tree for 2026: QLoRA SFT → DPO → GRPO when your reward is verifiableFuture AGIPolicy dependency / Stack layerIAPS warns on Kimi Claw: security and governance risks of Chinese-hosted 'always-on' AI agentsIAPSStack layer / Update threadsickn33/agentic-awesome-skills Hits 1,900+ Installable Agent Skills — and an Installer CLI to MatchGitHubThreat pattern / Follow-up threadClawHavoc campaign plants 300+ malicious skills on a single marketplace to run infostealersUnit 42 (Palo Alto Networks)Stack layer / ContrastOpenAI launches ChatGPT Work, an agentic workspace on GPT-5.6, with Sol/Luna/Terra model tiersInfoWorldStack layer / Threat patternDefend against prompt injection with an embedding-scored Threat Library, not brittle regex rulesPromptHaloStack layer / Threat patternAirflowAttack Fools Infrared Remote-Sensing VLMs With Physical PerturbationsarXivStack layer / Threat patternMeta Stands Up a Cloud Business to Sell AI Compute — CoreWeave Stock Drops 14%The Motley Fool