Source URL: https://simonwillison.net/2025/Mar/5/code-interpreter/
Source: Simon Willison’s Weblog
Title: Demo of ChatGPT Code Interpreter running in o3-mini-high
Feedly Summary: Demo of ChatGPT Code Interpreter running in o3-mini-high
OpenAI made GPT-4.5 available to Plus ($20/month) users today. I was a little disappointed with GPT-4.5 when I tried it through the API, but having access in the ChatGPT interface meant I could use it with existing tools such as Code Interpreter which made its strengths a whole lot more evident – that’s a transcript where I had it design and test its own version of the JSON Schema succinct DSL I published last week.
Riley Goodside then spotted that Code Interpreter has been quietly enabled for other models too, including the excellent o3-mini reasoning model. This means you can have o3-mini reason about code, write that code, test it, iterate on it and keep going until it gets something that works.
Code Interpreter remains my favorite implementation of the “coding agent" pattern, despite recieving very few upgrades in the two years after its initial release. Plugging much stronger models into it than the previous GPT-4o default makes it even more useful.
Nothing about this in the ChatGPT release notes yet, but I’ve tested it in the ChatGPT iOS app and mobile web app and it definitely works there.
Tags: riley-goodside, code-interpreter, openai, ai-agents, ai, llms, ai-assisted-programming, python, generative-ai, chatgpt
AI Summary and Description: Yes
Summary: The text discusses the recent availability of GPT-4.5 for Plus users, highlighting its integration with the Code Interpreter feature, particularly its use for programming tasks. The author appreciates the enhanced performance of the Code Interpreter with the o3-mini reasoning model, emphasizing its capabilities for coding tasks.
Detailed Description:
The text provides insights into the integration of OpenAI’s GPT-4.5 with the Code Interpreter feature, underlining key developments of interest to professionals working with AI and software development. Here are the major points:
– **GPT-4.5 Availability**: OpenAI released GPT-4.5 to Plus subscribers for a fee, introducing new functionalities that enhance user experience.
– **Code Interpreter Integration**: The author notes that the Code Interpreter can now leverage stronger reasoning capabilities with models like o3-mini, making it an effective tool for coding.
– **Coding Agent Functionality**: The Code Interpreter represents a successful implementation of a “coding agent” pattern, which allows iterative testing and refining of code.
– **User Experience**: The author mentions testing the Code Interpreter in the ChatGPT iOS and mobile web apps, signifying that these tools are accessible on different platforms.
– **Community Insights**: The mention of Riley Goodside highlights the collaborative aspect of the AI community, where users share insights about new capabilities.
Practical implications for security and compliance professionals:
– This development reiterates the importance of AI security in the context of coding agents, as these systems may unintentionally generate insecure code if not properly monitored.
– Professionals must consider the implications of generative AI in their workflows, particularly regarding code validation, vulnerability assessments, and the overall security of AI-assisted programming environments.
Overall, this development in AI tools represents an important evolution in the capabilities available to software developers and prompts a need for vigilance in security practices surrounding AI-generated content.