On June 1, GitHub Copilot switched to token-based billing. Developers are reporting bills 10x higher, with some burning through a month of credits in hours.
Meanwhile, a quieter shift has been underway. There's something for switchers at the end of this thread. 🧵
Use your SuperGrok or X Premium+ subscription in @kilocode.
Try grok-build-0.1 for high speed and agentic coding intelligence, available in the Kilo IDE extensions or CLI.
https://t.co/JGO8UQKKEB
What yesterday's response confirmed: developers want honest model tests with the prompt, the cost, and the output visible. Benchmarks and hot takes are not what's moving conversations anymore. We'll keep doing more of these.
We weren't done.
7 more sites we built with Grok Build 0.1 in Kilo Code: parrot translator, moon hotel booking, Pomodoro timer, CRT terminal, Shakespeare's GitHub, Tokyo weather, lemonade stand dashboard.
Full writeup with prompts, costs, and how each one actually works under the hood: https://t.co/oDCnAz5ZSN
@heygurisingh Prompting still matters a lot. The quality of the output still heavily depends on the context, constraints, goals, and instructions you give the model. Better prompting usually means less iteration, better reasoning, and more reliable results.