Home

DSPy RLM with MCP Code Mode
Jan 26, 2026 — DSPy’s RLM (Reinforcement Language Model) module lets LLMs write Python code instead of picking tools one at a time. Combined with mcp_use’s code_mode...
Replicating Anthropic's Agent Skills with DSPy
Jan 08, 2026 — Anthropic recently released their Agent Skills specification, a framework for teaching AI agents new capabilities through modular, reusable skill pack...
Building an AI Guardrail with Embeddings: Part 2
Jan 03, 2026 — In Building an AI Guardrail with Embeddings, we built a basic prompt injection detector using BGE embeddings and three MLP classifier heads. It worked...
Building an AI Guardrail with Embeddings
Jan 02, 2026 — LLMs are powerful, but they’re vulnerable. Prompt injection attacks can trick models into ignoring instructions, leaking data, or doing things they sh...
LokiBot Analysis
May 08, 2022 — Brief Introduction The initial delivery was via email, however this post is about analyzing the delivery stages, malware and some SECOPS fails from th...