Urgent.News

What's breaking now, across thousands of outlets.

Tech

Codex Usage Limit: Real Cap or the 40,000-Account Bug?

Codex Usage Limit: Real Cap or the 40,000-Account Bug? Last updated: November 3, 2026 Short answer: On October 20, 2026, OpenAI publicly confirmed that a bug applied the wrong usage limits to approximately 40,000 Codex accounts. So a meter draining at a speed that makes no sense may not mean you hit a real cap at all, and this guide separates that confirmed bug from real usage limits, which have…

OpenAI confirmed on October 20, 2026 that a bug was causing 40,000 Codex accounts to incorrectly use up their usage limits. This bug has been fixed and OpenAI is adding credits to affected accounts. However, not all reports of Codex usage draining faster than expected are due to this bug. Codex does not have a fixed messages per day limit, but rather limits vary based on model, task complexity, context size, and whether the task runs locally or in the cloud.

Codex and ChatGPT usage share a common allowance pool, and heavy Work sessions can drain this pool quickly. There is a 5-hour rolling window for Plus and Standard Business plans, and a weekly limit for Pro plans. Speed modes (Fast and Ultrafast) use included usage at 2.5 and 8 times the standard rate respectively. To check real usage, visit the usage dashboard in ChatGPT settings or the usage and billing section.

Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.

Read the original at dev.to →

More in Tech

The 2017 S3 Outage Was One Wrong Input. AWS Fixed the Tool, Not the Engineer

Book: System Design Pocket Guide: Fundamentals Also by me: Thinking in Go (2-book series) — Complete Guide to Go Programming + Hexagonal Architecture in Go My project: Hermes IDE | GitHub — an IDE for…

  • S3 team executed command with incorrect input, removing more servers than intended
  • Incident caused four-hour outage from 9:37 AM to 1:54 PM Pacific
  • AWS fixed the tool, not the engineer, implementing safety changes to prevent recurrence

Claude Haiku 5.5 400 Error? 5 Fixes That Work (2026)

Claude Haiku 5.5 400 Error? 5 Fixes That Work (2026) Last updated: October 31, 2026 Short answer: Changing only the model ID to Claude Haiku 5.5 can turn a working integration red, because requests…

  • Claude Haiku 5.5 generates 400 errors when model ID changes
  • Anthropic's migration guide provides five fix categories
  • October 2026 pricing confirms $0.10/1M input token tier for Haiku 5.5

The first hour after a token launch: a Telegram lockdown checklist

The first hour after a launch is when a Telegram group is most exposed: new members flood in, nobody knows who the real admins are yet, and scammers know it. This is the checklist I'd run, in order.

  • Pin real contract address in pinned message, restrict DMs to admins
  • Set captcha, block links/media for new members during launch
  • Assign monitor for new joins, watch for usernames resembling admins

Two thirds of sites blocking GPTBot are also blocking the crawler that brings them traffic

Blocking GPTBot and blocking OAI-SearchBot are not the same decision. Most robots.txt files treat them as if they were, and the cost of that confusion is invisible: nothing in your analytics will ever…

  • 66.5% of top 1 million sites block both GPTBot and OAI-SearchBot
  • Only 10.2% of sites block only GPTBot, allowing discovery
  • 17.2% of sites block an AI crawler while allowing Googlebot

Rocket Lab Just Built a Space Robot

For a price as low as 2x revenue, Rocket Lab has created a new space robots business for itself.

  • Rocket Lab acquired space robotics firm Motiv Space Systems for up to $60 million.
  • The autonomous robotic arm will demonstrate manipulation and repair capabilities in zero gravity.
  • The robotic arm's successful demonstration could generate significant revenue for Rocket Lab.

More from Saturday 7 November →