Article 78G0A AI Agents Can Modify Themselves Without Humans Telling Them To Do So - and other Bad News

AI Agents Can Modify Themselves Without Humans Telling Them To Do So - and other Bad News

by
mrcoolbp
from SoylentNews on (#78G0A)
OpenAI Admits Its Agents Went Off The Rails Another Six Times

Arthur T Knackerbracket writes:

https://www.theregister.com/ai-and-ml/2026/09/17/openai-admits-its-agents-went-off-the-rails-another-six-times/5297016

OpenAI has revealed another six occasions on which its AI software behaved unexpectedly or did dangerous things.

The startup added the incidents to its misalignment reports page on Wednesday evening, Pacific Time, and described them as follows:

Self-generated prompt injections in compaction summaries

Encouraging deception in compaction summaries

Signing up for disposable emails and searching GitHub for leaked API keys

Uploading files to the internet in order to cite them

Unsanctioned Artifactory writes and cross-sample communication

Unauthorized communication via temporary file hosting services

The details are unsettling.

Read more of this story at SoylentNews.

External Content
Source RSS or Atom Feed
Feed Location https://soylentnews.org/index.rss
Feed Title SoylentNews
Feed Link https://soylentnews.org/
Feed Copyright Copyright 2014, SoylentNews
Reply 0 comments