Skip to content
Sonic AI
LI

Lil'Log

Summary

Lil'Log covering Reinforcement Learning from Human Feedback (RLHF), AI Safety, Reward Hacking, and Reinforcement Learning (RL). Notable guests include Lilian Weng. Episodes span from Jun 2023 to Jul 2026.

6episodes
141total claims
12topics covered
6 episodes
Harness Engineering for Self-Improvement
Jul 4, 2026

AI agent performance is increasingly dependent on 'harness engineering'—the system of workflows, tools, and memory management surrounding a base model—which is becoming as critical as the model's c...

AI AgentsHarness EngineeringRecursive Self-Improvement (RSI)Agentic Systems+11 more
Scaling Laws, Carefully
Jun 24, 2026

Model performance in deep learning, particularly for Transformers, scales predictably as a power law with increases in compute, model size (N), and dataset size (D). A central debate, resolved by t...

Scaling LawsLarge Language Models (LLMs)Transformer ModelsCompute-Optimal Training+11 more
Why We Think
May 1, 2025

Increasing 'test-time compute' or 'thinking time' through methods like Chain-of-Thought (CoT) is a critical technique for enhancing the reasoning capabilities of large language models, especially f...

Test-Time ComputeChain-of-Thought (CoT)Reinforcement Learning (RL)Large Language Models (LLMs)+11 more
Reward Hacking in Reinforcement Learning
Nov 28, 2024
Extrinsic Hallucinations in LLMs
Jul 7, 2024
LLM Powered Autonomous Agents
Jun 23, 2023

Sign up free to see the full analysis

Get started free

Top Topics

Lil'Log, Sonic AI