LLM-as-Judge for Hallucination Detection: Does the Critic Agent Actually Work?
This is a follow-up to From arXiv to SEC: Building a Multi-Agent Financial Report Analyst with LangGraph. That post ended with: “The remaining question is...
Featured Projects
TORCS RL Racing Agent
9.7M steps of reinforcement learning in TORCS simulator. PPO, reward shaping, catastrophic forgetting — the full journey.
arXiv RAG System
End-to-end academic paper Q&A system built from scratch. FastAPI + ChromaDB + LLM, fully containerised with Docker.
FinScope - Multi-Agent Financial Analyst
Multi-agent RAG system for SEC EDGAR & Companies House filings. LangGraph orchestration, parallel analysis, hallucination check with retry loop.
DefectVision - Manufacturing Defect Detector
Real-time anomaly detection trained on normal images only. PatchCore, FastAPI inference API, Streamlit dashboard with webcam streaming.
Recent Posts
DefectVision: Building a Real-Time Manufacturing Defect Detector Trained on Normal Images Only
DefectVision: Building a Real-Time Manufacturing Defect Detector Trained on Normal Images Only
From arXiv to SEC: Building a Multi-Agent Financial Report Analyst with LangGraph
From arXiv to SEC: Building a Multi-Agent Financial Report Analyst with LangGraph
From Naval Architecture to AI: Why I Changed Everything
This is not a technical post. It is an account of how I ended up studying Data Science and AI at the University of Liverpool after four years of Naval Arc...
LoRA Fine-Tuning Qwen3 4B for RAG: A 6.8-Hour Experiment That Failed Honestly
This post is a deep dive into the fine-tuning experiment from the arXiv RAG System. That post summarised it in a section - this one documents every detail...