Might be interesting to evaluate it for structured data extraction from unstructured text, other than that I'm not sure what I might try it for beyond code (and SQL)
@simonw
-
Prompt Injection Attacks on LinkedIn: Vulnerability and Risk
By
–
It's delightful how easy it is to deploy working prompt injection attacks via LinkedIn
-
Open Source Revenue Sharing and Legal Framework Considerations
By
–
Then if the book later makes money you can pull the list of sponsors from GitHub (there's an export CSV button) to share proceeds with them Setting up a legal framework around this would be a whole lot more work though
-
GitHub Sponsors book workflow implementation strategy
By
–
An individual could implement most of this today on top of GitHub Sponsors: start a private repo for the book, set it so people who sponsor at a certain tier automatically gain access to that repo, write the book in there as Markdown, accept feedback via issues
-
GPT-5-Codex Prompting Guide: Best Practices for Code
By
–
Plus a new prompting guide for the GPT-5-Codex model "Because the model is trained specifically for coding, many best practices you once had to prompt into general purpose models are built in, and over prompting can reduce quality." https://
cookbook.openai.com/examples/gpt-5
-codex_prompting_guide
… -
OpenAI GPT-5-Codex Pricing Details Released
By
–
Here's the OpenAI details page for the gpt-5-codex model https://
platform.openai.com/docs/models/gp
t-5-codex
… It's priced at $1.25/million input and $10/million output – same as regular GPT-5 -
GPT-5-Codex Now Available Via Official OpenAI API
By
–
Looks like it's available via the official OpenAI API now as well – model ID is "gpt-5-codex"
-
Qwen releases multiple AI models in single blog post
By
–
… and two other things as well! Qwen released too much stuff today, I combined all four into a single blog post
-
Jevons Paradox in Software Development Capacity
By
–
Every company I've ever worked for has had a roadmap a mile long of stuff they'd love to build if only engineering time was cheaper I'm effectively talking here about the Jevons paradox applied to software development capacity
-
Voice Programming with AI Tools Boosts Developer Productivity
By
–
The more expertise you have the better the results you can get from AI programming tools, but crucially you don't need to type the code any more I'm very excited about how much you can get done as a programmer with voice alone today