Customers revolt as GitHub Copilot 'fixes' rate limits

📰 The Register

GitHub Copilot's token counting bug fix leads to rapid exhaustion of subscription allowances, forcing customers to reduce usage

intermediate Published 15 Apr 2026

Action Steps

Check current GitHub Copilot usage and subscription allowances
Review code generation habits to optimize token usage
Configure rate limiting settings to prevent unexpected exhaustion
Test and monitor token usage to avoid service disruptions
Apply changes to coding workflows to adapt to new rate limits

Who Needs to Know This

DevOps and software engineering teams using GitHub Copilot for AI-powered coding assistance will be impacted by the changes to token usage and rate limits

Key Insight

💡 A token counting bug fix in GitHub Copilot has led to rapid exhaustion of subscription allowances, requiring customers to adjust their usage and coding habits

Key Takeaways

GitHub Copilot's token counting bug fix leads to rapid exhaustion of subscription allowances, forcing customers to reduce usage

Full Article

Repair of bug that undercounted token usage leads to rapid exhaustion of subscription allowance Microsoft's GitHub last week told Copilot customers that they'd have to reduce their use of the AI service to ease the strain on company servers. This follows the company's discovery last month of a token counting bug that appears to have broken the company's pricing model.…

Read full article → ← Back to Reads