Teaching LLMs to Plan: Logical CoT Instruction Tuning for Symbolic Planning
Large Language Models (LLMs) like GPT and LLaMA have shown remarkable general capabilities, yet they consistently hit a critical wall when faced with structured symbolic planning. This struggle is esp...
5 Okt 202516min
Five Orders of Magnitude: Analog Gain Cells Slash Energy and Latency for Ultra-Fast LLMs
In this episode, we explore an innovative approach to overcoming the notorious energy and latency bottlenecks plaguing modern Large Language Models (LLMs).The core of generative LLMs, powered by Trans...
5 Okt 202517min
The Great Undertraining: How a 70B Model Called Chinchilla Exposed the AI Industry's Billion-Dollar Mistake
For years, a simple mantra has cost the AI industry billions: bigger is always better. The race to scale models to hundreds of billions of parameters—from GPT-3 to Gopher—seemed like a straight line t...
3 Aug 202513min
RewardAnything: Generalizable Principle-Following Reward Models
What if the biggest barrier to truly aligned AI wasn't a lack of data, but a failure of language? We spend millions on retraining LLMs for every new preference—from a customer service bot that must be...
3 Aug 202520min
AI That Evolves: Inside the Darwin Gödel Machine
What if an AI could do more than just learn from data? What if it could fundamentally improve its own intelligence, rewriting its source code to become endlessly better at its job? This isn't science ...
30 Jun 202528min
The AI Reasoning Illusion: Why 'Thinking' Models Break Down
The latest AI models promise a revolutionary leap: the ability to "think" through complex problems step-by-step. But is this genuine reasoning, or an incredibly sophisticated illusion? We move beyond ...
14 Jun 202512min
When AI Rewrites Its Own Code to Win: Agent of Change
Large Language Models have a notorious blind spot: long-term strategic planning. They can write a brilliant sentence, but can they execute a brilliant 10-turn game-winning strategy?This episode unpack...
13 Jun 202513min
Eureka: How AI Learned to Write Better Reward Functions Than Human Experts
Reward engineering is one of the most brutal, time-consuming challenges in AI—a "black art" that forms the very foundation of how intelligent agents learn. For decades, it's been a manual process of t...
7 Jun 202520min
