Image by Editor Contents# Introduction# Initial Setup# Wrapping Up # Introduction A harsh truth to begin with: textbook data science usually becomes a lie in the real world. Concepts and techniques are taught on finely curated, beautifully bell-curved data variables, but as soon as we venture into the wild of real projects, we are hit with lots of …
The “Robust” Data Scientist: Winning with Messy Data and Pingouin Read More »
In my first TDS post, I wrote about how to translate a real-world problem into an integer linear program. In my second, I wrote about how to make that program robust against uncertainty. Both were variations on the same idea: take a fuzzy real-world question, squeeze it into an LP, and let a solver do the rest. …
Image by Editor Contents# The Self-Hosted LLM Problem(s)# The Hardware Reality Check# Quantization: Saving Grace or Compromise?# Context Windows and Memory: The Invisible Ceiling# Latency Is the Feedback Loop Killer# Prompt Behavior Drifts Between Models# Fine-Tuning Sounds Easy Until It Isn’t# Final Thoughts # The Self-Hosted LLM Problem(s) “Run your own large language model (LLM)” is the “just start your own business” of …
Self-Hosted LLMs in the Real World: Limits, Workarounds, and Hard Lessons Read More »
in a situation where you have plenty of ideas on how to improve your product, but no time to test them all? I bet you have. What if I told you that you no longer have to do it all on your own, you can delegate it to AI. It can run dozens (or even …
Image by Author Contents# Introduction# 1. Transformers# 2. LangChain# 3. LlamaIndex# 4. vLLM# 5. Unsloth# 6. CrewAI# 7. AutoGPT# 8. LangGraph# 9. DeepEval# 10. OpenAI Python SDK# Comparing the 10 Libraries # Introduction Building large language model (LLM) applications is very different from using consumer-facing tools like Claude Code, ChatGPT, or Codex. Those products are great for end users, but when you want to build your own …
10 Python Libraries for Building LLM Applications Read More »
screening system checks a name against a watchlist, it faces a silent failure mode that nobody talks about. Type “Владимир Путин” into a system indexed on “Vladimir Putin” and most name-matching approaches return nothing. The two strings share zero characters, so edit distance is meaningless, phonetic codes fail (they assume Latin), and BM25 gives up …
Bytes Speak All Languages: Cross-Script Name Retrieval via Contrastive Learning Read More »
Image by Author Contents# Introduction# 1. Finance and Trading Bots# 2. Remote Coding and Dev Workflows# 3. Daily Briefings and Automations# 4. Personal Memory and Second-Brain Systems# 5. Research and Knowledge Pipelines# 6. Multi-Agent Systems# 7. Automating Business Operations# Final Thoughts # Introduction OpenClaw is quickly becoming one of the most talked-about open-source agent systems right now. But beyond the hype, the real question …
series about Reinforcement Learning (RL), following Sutton and Barto’s famous book “Reinforcement Learning” [1]. In the previous posts we finished dissecting Part I of said book, which introduces fundamental solution techniques which form the basis for many RL methods. These are: Dynamic Programming (DP), Monte Carlo methods (MC) and Temporal Difference Learning (TD). What separates …
Introduction to Approximate Solution Methods for Reinforcement Learning Read More »
Image by Editor Contents# Introduction# 1. OpenClaw# 2. OpenHands# 3. browser-use# 4. DeerFlow# 5. CrewAI# 6. LangGraph# 7. OpenAI Agents SDK# 8. AutoGen# 9. GPT Researcher (~26k ⭐)# 10. Letta# Wrapping Up # Introduction If you want to learn agent engineering by doing instead of just reading about it, the best way is still to fork real repos, run them locally, and change them for your own …
AI Engineering Hub Breakdown: 10 Agentic Projects You Can Fork Today Read More »
(TFL) is a statutory body responsible for London’s public transport network, managing buses, the Underground, Docklands Light Railway, Overground, and major roads. Their ‘Open Data’ policy means that they share much of their internal data with the public, which they say is currently powering over 600 apps for Londoners. One interesting data source they share …
Using Causal Inference to Estimate the Impact of Tube Strikes on Cycling Usage in London Read More »
