corpus.blog
42,180 blogs · 5,266,566 posts Claim your blog
Record · corpus.blog/posts/01a08c59-68e3-7240-8151-0438b85b08e5

2025-Era “Reward Hacking” Does Not Show that Reward Is the Optimization Target

turntrout.com · published 18 December 2025

A record is what was published and who pointed at it. The text of the post is not held here: read it at the source, or at its Wayback capture.

Read the post at turntrout.com Wayback capture
0blogs citing
First cited
—
Most recent
—
Rank this month
not ranked
External links
11
Words captured
2,102

Cited by

No blog we hold has cited this post yet.

Links from this post

Link
Host
https://arxiv.org/pdf/1606.06565
arxiv.org
https://redlib.catsarch.com/r/ClaudeAI/comments/1k30oip/i_stopped_using_37_because_it_cannot_be_trusted/
redlib.catsarch.com
https://arxiv.org/abs/2406.10162
arxiv.org
https://github.com/alexander-turner/TurnTrout.com/blob/7d6bd8d4c9f986d5758fb742868d7442b85718af/website_content/llms-cheat-a-lot.md
github.com
https://www.alignmentforum.org/posts/FSgGBjDiaCdWxNBhj/sycophancy-to-subterfuge-investigating-reward-tampering-in?commentId=GQEZcovfaugLMAgAW
alignmentforum.org
https://fatebook.io/q/an-rl-trained-system-will-spontaneously--cmj9cw91i0000126qbyahc5vr
fatebook.io
https://yoshuabengio.org/2023/05/22/how-rogue-ais-may-arise/
yoshuabengio.org
https://www.lesswrong.com/posts/k4AQqboXz8iE5TNXK/a-shot-at-the-diamond-alignment-problem?commentId=ikHq2AnuBTiCANCsi
lesswrong.com
https://www.lesswrong.com/posts/k4AQqboXz8iE5TNXK/a-shot-at-the-diamond-alignment-problem?commentId=o4xhieQnt5HxLmGDF
lesswrong.com
https://arxiv.org/abs/2203.02155
arxiv.org
https://alignmentforum.org/posts/whkMnqFWKsBm7Gyd7/recontextualization-mitigates-specification-gaming-without
alignmentforum.org
Elsewhere on turntrout.com (8)