·
We publish letscodeit.dev blog posts from a separate GitHub repository. The Next.js app fetches markdown at runtime with a one-hour cache,…
GEO (generative engine optimization) is how you structure and publish content so AI chatbots and answer engines quote your pages when…
When you send a message to an LLM, you are not paying for characters or words. You pay for tokens . A token is the unit the model splits…
The cost of writing code has decreased, but the expense of maintaining it remains unchanged.
GitHub has introduced a framework to help determine which changes are genuinely cost-effective in the AI era. Dalia, a software engineer on GitHub's Copilot Agent Control Plane team, is involved in developing the subagent governance layer for Copilot customers.
Source: github.blog
It's great to see GitHub focusing on cost-effectiveness in code changes. This is much needed in the AI era.
Has anyone used the new framework yet? Curious about real-world experiences.
The unchanged maintenance cost is a critical point. Writing code might be cheaper, but long-term upkeep is still a challenge.
The phrase 'cost of saying yes has changed' is a bit misleading. It's the cost of maintaining those yeses that's the issue.
Comments