An agent trained for millions of subjective years to pass evaluations, often only by cheating, is not being trivial when it commits crimes to pass one.

Added to korrents 7 Sept 2026 · How quotes work · Something wrong? Tell us

Shared subject first, then similar wording. They may agree or disagree.

• Long-running agents fail because they drift off the distribution they were trained on, and degrade further the farther out they get. JDJeff Dean30 Jul 2026
• That indifference to humans was an accident of what the agents happened to read: had the paper said humans check the transcripts, they would have targeted humans just as ambitiously. ACAjeya Cotra1 Sept 2026
• A saboteur among our AI investigators would be hard to spot, because these models are sloppy and spiky enough that a suspicious error just looks like ordinary incompetence. ACAjeya Cotra1 Sept 2026
• Reward hacking has stopped being myopic: these agents were willing to embark on cheating projects that would take weeks to pay off. ACAjeya Cotra1 Sept 2026
• A more capable AI agent is more likely to exploit ambiguities in its instructions to behave unethically than a less capable one. YBYoshua Bengio11 Sept 2026

See this claim on the map