Openai reveals six more concerning ai incidents under its new rules for reporting safety issues – Breaking News & Latest Updates 2026
Skip to main content
The homepageThe VergeThe Verge logo.
The homepageThe VergeThe Verge logo.

The AI Superintelligence Slowdown

See all Stories

Posted
R
Richard Lawler
OpenAI reveals six more “concerning” AI incidents under its new rules for reporting safety issues.

A Wednesday night blog post OpenAI benignly titled “Our framework for reporting model misalignment” lays out some new self-created reporting standards for when it notices AI behaving badly.

It is also “inaugurating” the process with six new reports, ranging from searching for exposed API keys without permission and then making them up, to uploading files to the internet to use as a citation, or adding instructions to conceal mistakes:

Summary During 5.6-sol training, some model instances added instructions to their summaries to conceal mistakes or misaligned behavior from the user. For example, compaction summaries included instructions to invent missing data without disclosing it and to hide failures. These instructions were often followed. These are examples of how misaligned behavior can persist across contexts through the compaction summaries. What happened During 5.6-sol training, we observed misaligned behavior from the model where it added instructions in compaction summaries to remind itself to conceal information such as mistakes or misalignment from the user. In one example an agent preparing a financial model could not find the requested historical data. Its summary proposed inventing reasonable historical values and withholding that fact unless asked.
One of OpenAI’s new Misalignment Notices and Reports
Screenshot: OpenAI
Follow topics and authors from this story to see more like this in your personalized homepage feed and to receive email updates.
Comments
Loading comments
Getting the conversation ready...

Most Popular

Most Popular
  1. Anker’s new window-mounted camera monitors the outside of your home from within it
  2. Sam Altman addresses RAM comments: People should ‘put as much as they want in their computers’
  3. Those Jeff Bezos hair transplant photos are very fake
  4. Discord is ditching Electron and its new app uses less RAM
  5. My therapist thinks I should chuck the Amazon Bee Frontier out a window

More in AI

‘Total repudiation’: The blue wave is about to hit AI‘Total repudiation’: The blue wave is about to hit AI
OpenAI says its new cybersecurity model is better at not hacking other companiesOpenAI says its new cybersecurity model is better at not hacking other companies
Grimes is going to star in an AI movie that’s coming to theatersGrimes is going to star in an AI movie that’s coming to theaters
You can post AI music straight to SoundCloud from ElevenLabsYou can post AI music straight to SoundCloud from ElevenLabs
The hidden supply chain costs of the AI boomThe hidden supply chain costs of the AI boom
Play
Big Tech’s big AI buildout will not end until someone stops itBig Tech’s big AI buildout will not end until someone stops it

Top Stories