Refining Language Models for Reliable Chatbots

15min Snip

00:00

Play full episode

Summary

Transcript

Episode notes

The chapter explores refining pre-trained language models to create reliable chatbots through Reinforced Learning from Human Feedback, aligning with user preferences to enhance performance. It discusses challenges extending this approach to broader agency creation and the importance of ground truth rewards in reinforcement learning. The conversation delves into training reward models to tackle the absence of ground truth rewards for human preferences and complex tasks, highlighting potential challenges in AI behavior.

LLMs are democratizing digital intelligence, but we’re all waiting for AI agents to take this to the next level by planning tasks and executing actions to actually transform the way we work and live our lives.

Yet despite incredible hype around AI agents, we’re still far from that “tipping point” with best in class models today. As one measure: coding agents are now scoring in the high-teens % on the SWE-bench benchmark for resolving GitHub issues, which far exceeds the previous unassisted baseline of 2% and the assisted baseline of 5%, but we’ve still got a long way to go.

Why is that? What do we need to truly unlock agentic capability for LLMs? What can we learn from researchers who have built both the most powerful agents in the world, like AlphaGo, and the most powerful LLMs in the world?

To find out, we’re talking to Misha Laskin, former research scientist at DeepMind. Misha is embarking on his vision to build the best agent models by bringing the search capabilities of RL together with LLMs at his new company, Reflection AI. He and his cofounder Ioannis Antonoglou, co-creator of AlphaGo and AlphaZero and RLHF lead for Gemini, are leveraging their unique insights to train the most reliable models for developers building agentic workflows.

Hosted by: Stephanie Zhan and Sonya Huang, Sequoia Capital

00:00 Introduction

01:11 Leaving Russia, discovering science

10:01 Getting into AI with Ioannis Antonoglou

15:54 Reflection AI and agents

25:41 The current state of Ai agents

29:17 AlphaGo, AlphaZero and Gemini

32:58 LLMs don’t have a ground truth reward

37:53 The importance of post-training

44:12 Task categories for agents

45:54 Attracting talent

50:52 How far away are capable agents?

56:01 Lightning round

Mentioned:

The Feynman Lectures on Physics: The classic text that got Misha interested in science.
Mastering the game of Go with deep neural networks and tree search: The original 2016 AlphaGo paper.
Mastering the game of Go without human knowledge: 2017 AlphaGo Zero paper
Scaling Laws for Reward Model Overoptimization: OpenAI paper on how reward models can be gamed at all scales for all algorithms.
Mapping the Mind of a Large Language Model: Article about Anthropic mechanistic interpretability paper that identifies how millions of concepts are represented inside Claude Sonnet
Pieter Abeel: Berkeley professor and founder of Covariant who Misha studied with
A2C and A3C: Advantage Actor Critic and Asynchronous Advantage Actor Critic, the two algorithms developed by Misha’s manager at DeepMind, Volodymyr Mnih, that defined reinforcement learning and deep reinforcement learning