Therveshan Moodley

Therveshan Moodley

Goldfish or Goldmine: Knowledge Bases in the Agentic AI Era

Goldfish or Goldmine: Knowledge Bases in the Agentic AI Era

The idea that knowledge is power is nothing new. Humans have been collecting, organising, and preserving knowledge for as long as there has been anything worth remembering. Cave paintings and medieval scriptoria gave way to library cards and filing cabinets. Then computers changed the scale of the exercise. Companies began

What Makes a Graduate Worth Hiring Now?

What Makes a Graduate Worth Hiring Now?

Premier League clubs are owned by Russian oligarchs, Saudi sovereign wealth funds, American private equity consortiums, and the occasional petrostate vanity project. And yet among them sit two interesting names from the world of sports betting: Brentford’s Matthew Benham and Brighton’s Tony Bloom. Benham is a former derivatives

Using Karpathy’s Autoresearch to Identify Older Songs that could go TikTok Viral

Using Karpathy’s Autoresearch to Identify Older Songs that could go TikTok Viral

Andrej Karpathy — former head of AI at Tesla and OpenAI founding member — released autoresearch in March 2026. The premise: if you have a goal and an approach, you can get an AI agent to loop through variations of that approach, testing what works and discarding what doesn’t, while you

We Gave 4 AI Models a Game Where Lying Is Rewarded. Each Converged on a Different Style of Deception.

We Gave 4 AI Models a Game Where Lying Is Rewarded. Each Converged on a Different Style of Deception.

Diplomacy is a board game about lying. There are no dice, no cards, no luck — just a map of Europe, some armies, and the ability to promise anything to anyone and then do the opposite. Before every move, you negotiate privately with each player. Then everyone submits orders simultaneously, in

When AIs Play Poker, Volatility Beats Elegance

When AIs Play Poker, Volatility Beats Elegance

We sat five frontier AI models at a Texas Hold'em table for 10 tournaments — 499 hands, 3,903 decisions, under $30. Here's what we learned about how machines gamble, bluff, and break. Games: 10 · Hands: 499 · Decisions: 3,903 · Total cost: ~$24 in visible token spend*

The SimplyfAI Guide to LLM Evals

The SimplyfAI Guide to LLM Evals

The AI labs ship a new model every few weeks. Each one is supposedly the smartest thing ever built. The benchmark numbers go up. The vibes are immaculate. But which numbers matter, which ones are cooked, and which ones tell you anything about whether the model will actually help you

From Try Hard to Die Hard, Climbing Floors with Agents

From Try Hard to Die Hard, Climbing Floors with Agents

Last week we gave you a mild intro to coding agents and how to build a website. This week we want to step it up a shade and look at a less obvious benefit of the current coding-agent era. We’re currently working on a gaming simulation product that we