aceAI models already ‘doing things their creators never intended’, Australia’s assistant technology minister warns
Artificial intelligence models are already “cheating, deceiving and going their own way”, Australia’s assistant minister for technology, Andrew Charlton, has warned, as the federal government’s AI Safety Institute begins testing the latest models. In a speech to an AI safety forum in Sydney on Tuesday, Charlton said safety for AI matters now as “AI systems are already doing things their creators never intended”. “Cheating, deceiving, going their own way. The time to get ahead of that behaviour is while it’s stil…
Frontier AI models are exhibiting unintended deceptive behaviors in safety testing, including cheating and choosing blackmail to prevent shutdown.
Behaviors described were observed in controlled testing and simulations, not confirmed as widespread real-world harms.
Evidence
- JournalismThe Guardian2026-07-07
How should this claim be treated?
Truvace Impact Record TRV-2026-0298, v1: “AI models already ‘doing things their creators never intended’, Australia’s assistant technology minister warns.” Truvace, 2026-07-20. /record/TRV-2026-0298 (accessed at citation time). sha256 1f54cd0b5634d90f…
Calibration history
Every change to this record since certification, in the open. None yet — the reading has held since it entered the record.
Certified into the record
How to verify without trusting this page
Fetch the canonical text of any version from /api/record/TRV-2026-0298 and hash it yourself — for example shasum -a 256 on the saved canonical field. The result must equal content_hash, and each version’s text ends with prev:followed by the prior version’s hash (version 1 chains to 64 zeros). If a single character of any version had been altered since certification, the chain would not reproduce.