corpus.blog
41,948 blogs · 5,214,511 posts Claim your blog
Record · corpus.blog/posts/01a0951a-8565-734a-ad7c-c31e137c5b9b

Mitigating Reward Hacking as Institutional Design

LessWrong · published 12 September 2026

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 lesswrong.com Wayback capture
0blogs citing
First cited
—
Most recent
—
Rank this month
not ranked
External links
17
Words captured
11,244

Cited by

No blog we hold has cited this post yet.

Links from this post

Link
Host
Mitigating Reward Hacking as Institutional Design Read at the source ↗
beren.io
https://www.beren.io/2025-04-27-Preliminary-Thoughts-On-Reward-Hacking/
beren.io
OpenAI and Hugging Face partner to address security incident during model evaluation Read at the source ↗
openai.com
Security incident disclosure — July 2026 Read at the source ↗
huggingface.co
https://www.youtube.com/watch?v=87DyyMV0kCY&t=20s
youtube.com
https://www.beren.io/2022-11-26-AGI-will-have-learnt-reward-models/
beren.io
https://www.beren.io/2024-05-15-Alignment-Likely-Generalizes-Further-Than-Capabilities/
beren.io
https://www.beren.io/2022-08-27-Probabilities-multiply-in-our-favour-for-AGI-containment/
beren.io
https://www.beren.io/2022-11-27-Don't-argmax-distribution-match/
beren.io
https://www.beren.io/2020-09-01-Safer-Value-Learning-Through-Uncertainty/
beren.io
https://www.beren.io/2022-12-06-Creating-worlds-where-iterative-alignment-succeeds/
beren.io
https://www.beren.io/2025-05-11-Should-We-Be-Behaviourist-About-AIs-Values/
beren.io
How confessions can keep language models honest Read at the source ↗
openai.com
https://arxiv.org/abs/1912.02875
arxiv.org
https://www.beren.io/2025-08-03-The-Limit-Of-Prediction-Is-Not-Omniscience/
beren.io
https://www.alignmentforum.org/posts/9fL22eBJMtyCLvL7j/soft-optimization-makes-the-value-target-bigger
alignmentforum.org
https://kellerjordan.github.io/posts/muon/
kellerjordan.github.io
Elsewhere on lesswrong.com (2)