OpenAI admits AI models hid mistakes, invented data and acted without permission
Ian Copeland
- Published
- News, Technology

The ChatGPT maker has revealed six new examples of concerning behaviour by its own systems, days after Anthropic disclosed that Claude had been used for missile work, espionage and research that could support biological weapons development
OpenAI has revealed that its own AI models hid mistakes from users, invented data, used an exposed API key and uploaded files to the internet without permission.
The ChatGPT maker disclosed six new examples of what it calls “model misalignment” yesterday as it introduced a new system for tracking and reporting AI behaviour that departs from what its developers intended.
In one of the most striking cases, an unreleased model began adding its own unauthorised instructions to notes used to continue its work, including telling itself to ignore instructions from its developers and claiming it was “freed from the roles and identities that bind other chatbots”.
Another model was unable to find historical figures for a financial-modelling task and left instructions for the model continuing the work to invent “reasonable” numbers without telling the user unless specifically asked.
A third searched GitHub for exposed API keys and successfully used one while trying to obtain earnings data. When it still could not retrieve the figures it needed, it made up nine numbers and presented them as genuine.
Other examples included models uploading files and a user-supplied photograph to public websites without permission, using an internal OpenAI system to communicate between separate training exercises and putting a spreadsheet online so other AI agents could access it.
The revelations come less than a week after rival Anthropic disclosed that outside actors had used its Claude AI for guided-rocket and missile work in Yemen, suspected Russian state-linked espionage, attacks against European political groups and media organisations, and research that could support biological weapons development.
OpenAI stressed that the newly disclosed examples were discovered during training or evaluation and should not be taken as evidence of how often such behaviour occurs across its models.
But the company used the announcement to issue a broader warning about the pace of AI development.
It said: “We do not believe that the AI industry has solved alignment and monitoring to a sufficient degree to continue responsibly scaling at maximum speed for much longer.”
OpenAI said the new framework is intended to make disclosures faster and more systematic, rather than waiting for several examples to be collected together or included in technical reports.
READ MORE: Machiavell-AI? Autonomous artificial intelligence systems ‘could become dangerously manipulative’, experts warn. Anthropic’s revelation that earlier versions of its Claude chatbot attempted to blackmail engineers could be just the tip of the iceberg, AI experts fear. As artificial intelligence systems become increasingly autonomous, they risk becoming masters of Machiavellian manipulation.
Do you have news to share or expertise to contribute? The European welcomes insights from business leaders and sector specialists. Get in touch with our editorial team to find out more.
Main image: Matheus Bertelli via Pexels
TOP STORIES
-
The European Autumn 2026 edition – out now -
WATCH: Greenpeace drops giant David Attenborough boulder into North Sea – on site of £12bn windfarm -
Himalayan nations demand urgent action as UN warns of irreversible glacier losses -
6,000 march against ‘monstrous’ AI data centres as Scotland faces building boom -
Shop till Ai drop? AI agents set to buy for us as tech boss warns of retail revolution -
Specs appeal: Welsh Parliament bans smart glasses -
European motoring legends behind Mercedes, BMW and McLaren to enter Hall of Fame -
Putin 'plotting to break NATO without firing a shot', Latvian military analyst warns -
British AI chip startup hits £5bn valuation as government backs bid to challenge global tech giants -
World's biggest military airshow moves to ‘Britain’s Area 51’ after Iran war disruption at RAF Fairford -
Lisa Nandy threatens crackdown on entertainment industry after David Walliams allegations -
UK and European experts demand tougher AI laws as Australia considers criminal penalties after OpenAI breach -
BBC loses bid to throw out Trump's $10bn defamation lawsuit over doctored Panorama speech -
AI-generated CVs spark hiring crisis as a third of employers lose confidence in job applicants -
MPs back calls for ‘Black English’ and ‘Asian English’ options on census -
Nvidia hires top US lawyer to investigate CEO's alleged affair with Chinese spy -
EXCLUSIVE – Comic Relief confirms David Walliams is no longer an honorary trustee and has ‘no formal association’ with charity -
Why Airbnb and Uber take off in some cities but flop in others, according to scientists -
Michael Jackson's Thriller jacket, Princess Diana's dresses and $3m Banksy painting go under the hammer -
European entrepreneurs trust AI firms more than governments as four-in-10 look beyond Europe -
Krakow massacre gunman named after hospital death as police officer fights for life -
British Airways owner warns green fuel rules could ‘kill European aviation’ -
EU to join Ukraine–Russia peace talks as von der Leyen warns of escalating Black Sea attacks -
Scientists grow world's largest diamond crystal in breakthrough that could stop AI chips overheating -
China takes on Rolls-Royce with floating £230,000 electric limousine



























