Geiger inventories local #AI agents and #MCP configuration, with baseline comparisons for drift. No model or #API account needed. It reads configuration, not runtime behavior.
https://t.co/e4eJhuXR3D
#AISecurity#MCPSecurity
Review #AI-agent skills before installing them. SkillSpector checks for dangerous code, prompt-injection patterns and #MCP risks. Static scans need no paid model #API; findings still need review.
https://t.co/aBqpNV5OC2
#AISecurity#OpenSource
Crouching VRAM, Sleeping Dragon: How the Strata Family Makes Massive AI Models Run by Waking Only What They Need
https://t.co/tdvhprr1BS
#strata#glm#localLLM#inference#nvidia#rtx5090
The Quantization Tax Nobody Charged: #Qwen 3.8 27B Q4 Quant Matches Its Published Scores on a Single #RTX5090@Alibaba_Qwen
https://t.co/yL4yCzZmJr
https://t.co/yjU9qmV5B2
#localLLM
Everyone budgets a quality tax for 4-bit quants. I went looking for it on #Qwen 3.8 27B: GPQA, IFBench, 95 real CVEs, RULER at 262K, KL-divergence.
The tax never showed up — Q4 matches @Alibaba_Qwen 's published BF16 scores on a single #RTX5090.
https://t.co/MxhfDofJjV
#localLLM
PyDiffWatch: watches the PyPI release firehose, diffs every new version, flags suspicious ones fast enough to report for takedown.
▸never runs what it inspects – packages are data, not code
▸reviews run on a local LLM
https://t.co/sg937IrbCg
@ramimacisabird@abh1sek@anantshri