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 1 Sept 2026 · How quotes work · Something wrong? Tell us

Related korrents

Our reading — they may agree, disagree or merely touch the same thing. Closest first: a shared subject counts for most, then how near the wording is.

• 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 2026similar wording
• 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 2026similar wording
• 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 2026similar wording
• 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 2026similar wording
• Agency and clock speed beat domain experience in a hire, and in a fast-moving field experience is often a crutch of habits that need discarding. ACAlbert Cheng5 Oct 2025similar wording

On the map

Open the map on its own page →