Yes! This is the standard I've most wanted – a formalized, standardized JSON API for talking to models Would have been nice to see it build on chat completions since everyone's implemented that already, but Responses offers a clean slate and is a better fit for recent models
@simonw
-
Microsoft Copilot vs GitHub Copilot: Enterprise Licensing Differences
By
–
Is the Microsoft product called Copilot the same thing as GitHub's product called Copilot? If you buy the Microsoft enterprise Copilot do you get a working GitHub Copilot subscription automatically?
-
Redefining useful work in the AI-powered development era
By
–
I'm hoping this is a teething period while teams figure out how to operate effectively in the weird new normal – the cost of churning out issues and code has dropped so much, now we need new standards for what "useful work" looks like
-
Claude Code Self-Documentation Access Pattern for LLMs
By
–
It's neat how if you ask Claude Code questions about itself it can answer them, because it knows how to fetch a Markdown index of its own online documentation and then navigate to the right place I wish more LLM tools would implement the same pattern!
-
Claude Code system prompt startup integration concerns
By
–
I don't know if it is guaranteed that Claude Code will read that stuff directly into the system prompt on startup
-
GitHub patterns for maintaining duplicate markdown files
By
–
What are the best patterns for maintaining an identical http://
claude.md and http://
agents.md in the same GitHub repository? Is there a symlinking trick that works? Can you have one of them just say "go read the other one"? Or is it worth automating copying them? -
Surgeon Approach More Productive Than Code Review
By
–
Depending on how you do it, I think the surgeon approach can actually be more productive than if you are mainly reviewing code Code review is a lot quicker if you already know the rough shape it's meant to be because you were hands on in helping design and guide it
-
Programmers Must Learn AI Tools or Face Career Risks
By
–
The real danger is for programmers who say "but I don't want to be a manager, so I'm not going to figure out how to use this stuff on principle!"
-
Managing AI Systems Differs from Human Team Leadership
By
–
Disagree. The hardest parts of management involve dealing with people. Working with AI is different because your "direct reports" will never get frustrated or discouraged or resistant to feedback Working with AI is more like being a tech lead, but I like the surgeon analogy more
-
Surgeon Model: Leverage Expertise Through Automation Support
By
–
"A surgeon isn't a manager, they do the actual work! But their skills and time are highly leveraged with a support team that handles prep, secondary tasks, admin. The surgeon focuses on the important stuff they are uniquely good at."