SkillsSkill 6: Fine-Tune Phi-4-Reasoning-Vision-15B Locally with Unsloth + LoRAUnsloth·medium signalXBlueskyLinkedInCopy link1. Install prerequisites: Python 3.8+, PyTorch with CUDA, `pip install unsloth transformers datasets`SourceSource pageUnsloth↳ Follow the threadPolicy dependency / Update threadMicrosoft Agent Framework dotnet-1.21.0 lands four breaking changes at once, including limiting MCP skill archives to ZIPGitHubPolicy dependency / Stack layerRIPPLE: an edit confined to one prompt-policy segment changes downstream behavior, so replay candidate edits after previously accepted ones before persistingarXiv 2609.12127Stack layer / Threat patternElva Launches Against Postman With Flat Workspace Pricing and Specs Generated From Repo CommitsElva (surfaced via the Product Hunt daily leaderboard for 2026-09-14)Policy dependency / Stack layerA replay of 68,266 real Claude Code requests says plain LRU beats the clever KV-cache policiesGitHubPolicy dependency / Stack layerSGLang Hit With Unauthenticated Pickle RCE via /update_weights_from_tensor, the Fourth Critical Inference-Stack CVE in Four WeeksCERT Coordination CenterStack layerRemoving AI slop is now its own tool category, with a 9,394-star repo and a fresh Show HN on the same dayGitHub TrendingPolicy dependency / Stack layergit-ai is a Git extension that tracks which code in your repo was AI-generated, at 140 open PRs to 71 issuesGitHub TrendingPolicy dependency / Stack layerTraceCrate v0.2 reads Claude Code, Codex and OTLP traces in one local workbenchGitHub