Category: GPT-4
-
Inside the Launch of GPT-4
With GPT-4 now stepping back from its starring role in ChatGPT, I want to share a few of my favorite memories from its launch. I originally joined OpenAI as an engineer on the Applied team, but later moved into a hybrid role as OpenAI’s “science communicator.” That shift let me…
-
Can You Dramatically Improve Results on the Latest Large Language Model Reasoning Benchmark With a Simple Prompt?

tldr: Yes. A recent paper, GSM-Symbolic: Understanding the Limitations of Mathematical Reasoning in Large Language Models, makes the claim that their new benchmark demonstrates that state of the art reasoning models have critical limitations when it comes to reasoning. Putting aside the fact that they grouped together tiny 2.7 B…
-
Improving GPT-4’s Visual Reasoning with Prompting

TLDR: How to boost GPT-4 with Vision’s capabilities with a simple prompt addition. A recent paper How Far Are We from Intelligent Visual Deductive Reasoning? points out the limitations in visual reasoning in image models like GPT-4V. Like other related papers, I think the investigators are directionally correct (these models…
-
Is the Reversal Curse Real?

A recent paper The Reversal Curse points out an apparent failure in large large language models like GPT-4. From the abstract: We expose a surprising failure of generalization in auto-regressive large language models (LLMs). If a model is trained on a sentence of the form “A is B”, it will not automatically…
-
My Custom Instructions for ChatGPT

tldr: Custom instructions let you provide ChatGPT with relevant information of your choice about you and how you like to communicate. I’ve use a couple simple tricks to adapt it to my style. I use ChatGPT non-stop for work, fun and exploring. When I write novels it’s a great research…
-
How to get GPT-4 to play Wordle (and other prompt tricks)

tl;dr: One of the tricks to using GPT-4 well is understanding how it sees text and instructions When we started testing GPT-4 internally last summer one of the first tests people would try is getting it to play the game Wordle. While trying to guess a five-letter word should be…