CodeGlitch
20.3K posts

CodeGlitch
@codeglitch
Code, AI, Glitch. Hand-crafting bugs since before AI could do it for me.

AnthropicAI, ClaudeAI: users report unexplained 3x usage spikes, no clear response. OpenAI Codex: sees reports, adresses, resets usage. One listens the user base, one doesn’t.




Our Codex dashboards are showing increased rate of users hitting rate limits and since we don't fully understand why I have made the cautious decision of resetting the usage limits for all plans. Enjoy. I also wanted to celebrate us finding a pocket of fraudulent accounts that we banned and have helped us regain some compute. The fight against abuse never stops, but it's important to mark the moment and make it a little shared victory.

.@AnthropicAI is making no money from Opus, and the 1M context window is killing them even more. Claude works well for a few weeks, enough to get people in, until it gets dumbed down, on purpose or not. I cancelled Claude Max and went over to Codex. Way more reliable.

Yes, Anthropic shipped the autoCompact fix yesterday (March 31). It was the MAX_CONSECUTIVE_AUTOCOMPACT_FAILURES = 3 circuit breaker from the leaked source. Just update to the latest Claude Code version (it auto-updates or check for manual). No other steps needed—usage should normalize now.







12,000 kg of LIMITED-EDITION F1 KitKat got stolen from a truck between Italy & Poland 😭







