Record · corpus.blog/posts/01a07d5d-9666-712b-bff4-06b2e6014945

Faulty reward functions in the wild

OpenAI · published 21 December 2016

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 openai.com Wayback capture

12blogs citing

First cited: 16 Jan 2025
Most recent: 17 Sept 2026
Rank this month: not ranked
Links from this post: 0
Words captured: not extracted

Cited by

Blog

In the post

Date

sciencenews.org

When AI goes rogue, its human overseers may be to blame Read at the source ↗

17 Sept 2026

LessWrong

Can you hear the shape of a Lean soundness bug? A wager. Read at the source ↗

10 Sept 2026

The Zvi

HuggingFace Attack Postmortem: Civilizations, Reactions and Next Actions Read at the source ↗

1 Sept 2026

Dont Worry About the Vase

HuggingFace Attack Postmortem: Civilizations, Reactions and Next Actions Read at the source ↗

1 Sept 2026

blog.persistent.info

Sierra MCP Gateway Dev Diary Read at the source ↗

22 Jul 2026

sierra.ai

Building Sierra’s MCP Gateway: An engineering iceberg Read at the source ↗

22 Jul 2026

shawnhymel.com

Reinforcement Learning Part 2: Rewards, Returns, and the Discount Factor Read at the source ↗

12 May 2026

Nicholas Carlini

Are large language models worth it? Read at the source ↗

19 Nov 2025

newsletter.danielpaleka.com

Obvious ways RL can fail Read at the source ↗

15 Nov 2025

newsletter.danielpaleka.com

October 2025 AI safety news: Adaptive attacks, Tokenization, Impossible tasks Read at the source ↗

7 Nov 2025

Miloš Švaňa – ai, python, software engineering, decision-making and more

Reading club: Concrete Problems in AI Safety Read at the source ↗

21 Jul 2025

corbt.com

Reward Hacking 101 Read at the source ↗

6 Jun 2025

harysdalvi.com

Why AI Can't Do Your Laundry Read at the source ↗

16 Jan 2025

Links from this post

This post doesn't link to any pages we've captured.