From 96b116203b1d177446dbaa2a3fbf5af7aa2cf25d Mon Sep 17 00:00:00 2001 From: Benjamin Klieger Date: Sun, 15 Sep 2024 18:58:57 -0700 Subject: [PATCH] improve docs again --- README.md | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/README.md b/README.md index 148d1e8..3f3f08d 100644 --- a/README.md +++ b/README.md @@ -4,7 +4,10 @@ This is an early prototype of using prompting strategies to improve the LLM's reasoning capabilities through o1-like reasoning chains. This allows the LLM to "think" and solve logical problems that usually otherwise stump leading models. Unlike o1, all the reasoning tokens are shown, and the app uses an open source model. -g1 is experimental and being open sourced to help inspire the open source community to develop new strategies to produce o1-like reasoning. This is an experiment to show the power of prompting reasoning in visualized steps, not a comparison to or full replication of o1, which uses different techniques. OpenAI's o1 is instead trained with large-scale reinforcement learning to reason using Chain of Thought, achieving state-of-the-art performance on complex PhD-level problems. g1 demonstrates the potential of prompting alone to overcome straightforward LLM logic issues like the Strawberry problem, allowing existing open source models to benefit from dynamic reasoning chains and an improved interface for exploring them. +g1 is experimental and being open sourced to help inspire the open source community to develop new strategies to produce o1-like reasoning. This experiment helps show the power of prompting reasoning in visualized steps, not a comparison to or full replication of o1, which uses different techniques. OpenAI's o1 is instead trained with large-scale reinforcement learning to reason using Chain of Thought, achieving state-of-the-art performance on complex PhD-level problems. + +g1 demonstrates the potential of prompting alone to overcome straightforward LLM logic issues like the Strawberry problem, allowing existing open source models to benefit from dynamic reasoning chains and an improved interface for exploring them. + ### Examples