3Simon Willison's Weblog·
Simon Willison quotes Thibault Sottiaux on a bad Codex bug
Simon Willison's blog references a quote from Thibault Sottiaux regarding a significant bug in OpenAI's Codex. The body content is not available in the provided text, but the title suggests a notable defect or failure mode in Codex was identified. This is a brief signal item pointing to a potential reliability or safety issue with an AI coding tool.
Related guides (3)
Related events (8)
Introducing Codex
OpenAI has announced Codex, a new product or capability targeting software development and coding tasks. The announcement comes from OpenAI's official blog, suggesting a significant product or model release. The body content was not provided, but given the Codex name and OpenAI's history, this likely involves an AI-powered coding agent or updated code generation system. Further details on capabilities, pricing, and availability are expected in the full announcement.
Why Codex Security Doesn't Include a SAST Report
OpenAI explains the design rationale behind Codex Security's approach to vulnerability detection, which forgoes traditional Static Application Security Testing (SAST) in favor of AI-driven constraint reasoning and validation. The post argues this approach surfaces real vulnerabilities while reducing false positives compared to conventional static analysis tools. This represents a substantive technical position on how LLM-based code analysis differs from rule-based security scanning.
Running Codex Safely at OpenAI
OpenAI published a blog post describing the security architecture used to run Codex as a coding agent internally, covering sandboxing, human approval workflows, network policies, and agent-native telemetry. The post is aimed at supporting enterprise adoption of coding agents by demonstrating safe and compliant deployment patterns. It provides operational detail on how OpenAI itself governs agentic code execution in production.
OpenAI Publishes System Card Addendum for Codex Agent and codex-1 Model
OpenAI released an addendum to the o3 and o4-mini system cards covering Codex, a cloud-based coding agent powered by codex-1—a variant of o3 fine-tuned for software engineering via reinforcement learning on real-world coding tasks. codex-1 is designed to produce code matching human style and PR conventions, follow instructions precisely, and iterate on tests until they pass. The addendum provides safety and capability documentation for this specialized agentic deployment.
Quoting Armin Ronacher
Simon Willison quotes Armin Ronacher in a brief commentary post. The body content is empty, so the specific substance of the quote is unavailable, but given the source and subjects involved—both prominent figures in Python/developer tooling communities who have written extensively about AI coding tools and agents—the post likely touches on AI-assisted development or related tooling themes.
Quoting Mitchell Hashimoto
Simon Willison quotes Mitchell Hashimoto in a brief commentary post. The body content is empty, so the specific substance of the quote is unavailable from this record. Given the source and context, it likely relates to AI tooling or developer workflows given Hashimoto's recent work on AI-assisted development.
Simon Willison quotes Andrej Karpathy
Simon Willison's blog features a quote from Andrej Karpathy, though the body content is not available for review. Given the source and the individuals involved, this likely captures a notable observation from Karpathy on AI/ML topics. Karpathy is a prominent voice in the field whose commentary frequently carries signal for practitioners.
Introducing upgrades to Codex
OpenAI has announced upgrades to Codex, its AI coding agent, improving speed, reliability, and real-time collaboration capabilities. The updates extend Codex's reach across multiple development environments including terminal, IDE, web, and mobile. The announcement emphasizes both interactive collaboration and autonomous task execution.