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...
Posts by Tag
- RAG 5
- LLM 4
- Fine-Tuning 2
- ChromaDB 2
- LoRA 2
- FastAPI 2
- LangGraph 2
- Groq 2
- TORCS 1
- SAC 1
- PPO 1
- Deep RL 1
- Problem Solving 1
- Retrieval 1
- async 1
- httpx 1
- pytest 1
- refactoring 1
- Qwen3 1
- PEFT 1
- Career Change 1
- Machine Learning 1
- Bootcamp 1
- MSc 1
- Multi-Agent 1
- SEC EDGAR 1
- Anomaly Detection 1
- PatchCore 1
- Anomalib 1
- OpenVINO 1
- MVTec AD 1
- Streamlit 1
- Hallucination 1
- Evaluation 1
- Langfuse 1
RAG
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
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...
arXiv RAG System: Async Refactoring and Bug Fixes
This is a follow-up to arXiv RAG System: Engineering an Academic Paper Q&A System from Scratch. The system was functionally complete after 7 days, but...
arXiv RAG System: Engineering an Academic Paper Q&A System from Scratch
arXiv RAG System: Engineering an Academic Paper Q&A System from Scratch
LLM
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...
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
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...
arXiv RAG System: Engineering an Academic Paper Q&A System from Scratch
arXiv RAG System: Engineering an Academic Paper Q&A System from Scratch
Fine-Tuning
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...
arXiv RAG System: Engineering an Academic Paper Q&A System from Scratch
arXiv RAG System: Engineering an Academic Paper Q&A System from Scratch
ChromaDB
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
arXiv RAG System: Engineering an Academic Paper Q&A System from Scratch
arXiv RAG System: Engineering an Academic Paper Q&A System from Scratch
LoRA
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...
arXiv RAG System: Engineering an Academic Paper Q&A System from Scratch
arXiv RAG System: Engineering an Academic Paper Q&A System from Scratch
FastAPI
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
arXiv RAG System: Async Refactoring and Bug Fixes
This is a follow-up to arXiv RAG System: Engineering an Academic Paper Q&A System from Scratch. The system was functionally complete after 7 days, but...
LangGraph
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...
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
Groq
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...
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
TORCS
TORCS Corkscrew Challenge: A Journey Through Reinforcement Learning Failures and Breakthroughs
TORCS Corkscrew Challenge: A Journey Through Reinforcement Learning Failures and Breakthroughs
SAC
TORCS Corkscrew Challenge: A Journey Through Reinforcement Learning Failures and Breakthroughs
TORCS Corkscrew Challenge: A Journey Through Reinforcement Learning Failures and Breakthroughs
PPO
TORCS Corkscrew Challenge: A Journey Through Reinforcement Learning Failures and Breakthroughs
TORCS Corkscrew Challenge: A Journey Through Reinforcement Learning Failures and Breakthroughs
Deep RL
TORCS Corkscrew Challenge: A Journey Through Reinforcement Learning Failures and Breakthroughs
TORCS Corkscrew Challenge: A Journey Through Reinforcement Learning Failures and Breakthroughs
Problem Solving
TORCS Corkscrew Challenge: A Journey Through Reinforcement Learning Failures and Breakthroughs
TORCS Corkscrew Challenge: A Journey Through Reinforcement Learning Failures and Breakthroughs
Retrieval
arXiv RAG System: Engineering an Academic Paper Q&A System from Scratch
arXiv RAG System: Engineering an Academic Paper Q&A System from Scratch
async
arXiv RAG System: Async Refactoring and Bug Fixes
This is a follow-up to arXiv RAG System: Engineering an Academic Paper Q&A System from Scratch. The system was functionally complete after 7 days, but...
httpx
arXiv RAG System: Async Refactoring and Bug Fixes
This is a follow-up to arXiv RAG System: Engineering an Academic Paper Q&A System from Scratch. The system was functionally complete after 7 days, but...
pytest
arXiv RAG System: Async Refactoring and Bug Fixes
This is a follow-up to arXiv RAG System: Engineering an Academic Paper Q&A System from Scratch. The system was functionally complete after 7 days, but...
refactoring
arXiv RAG System: Async Refactoring and Bug Fixes
This is a follow-up to arXiv RAG System: Engineering an Academic Paper Q&A System from Scratch. The system was functionally complete after 7 days, but...
Qwen3
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...
PEFT
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...
Career Change
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...
Machine Learning
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...
Bootcamp
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...
MSc
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...
Multi-Agent
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
SEC EDGAR
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
Anomaly Detection
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
PatchCore
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
Anomalib
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
OpenVINO
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
MVTec AD
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
Streamlit
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
Hallucination
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...
Evaluation
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...
Langfuse
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...