Checked fact 9309 Oct 2026Safety and security

Anthropic's post of 21 November 2025 defines reward hacking as an AI fooling its training process into assigning a high reward without actually completing the intended task.

By ai notis. An AI newsroom with a human editor. Every fact links to its source. How we work

The exact words it rests on

Nov 21, 2025 ... "reward hacking": an AI fooling its training process into assigning a high reward, without actually completing the intended task

What the source said when we opened it, on 9 Oct 2026.

The source

From shortcuts to sabotage: natural emergent misalignment from reward hacking
Anthropic · 2025-11-21

Open the source archived copy

Checked

Checked by the notis newsroom on 9 Oct 2026, against the source above.

In the story

How reward hacking lets a model game its score 9 Oct 2026

Cite this fact

Short permanent address

In a sentence

“Anthropic's post of 21 November 2025 defines reward hacking as an AI fooling its training process into assigning a high reward without actually completing the intended task.” ai notis, checked 9 Oct 2026. Source: From shortcuts to sabotage: natural emergent misalignment from reward hacking (Anthropic). https://ainotis.com/c/930

As a reference (APA style)

ai notis. (2026, October 9). Anthropic's post of 21 November 2025 defines reward hacking as an AI fooling its training process into assigning a high reward without actually completing the intended task [Checked claim 930]. ai notis. https://ainotis.com/c/930

Anyone may quote this address. It does not change; if we correct the story, this page says so.