Start / LessWrong (30+ Karma) / Linkpost metr recent frontier models are reward hacking by daniel kokotajlo

LessWrong (30+ Karma)

[Linkpost] “METR: Recent frontier models are reward hacking” by Daniel Kokotajlo

1 min • 9 juni 2025
This is a link post.

METR just made a lovely post detailing many examples they've found of reward hacks by frontier models. Unlike the reward hacks of yesteryear, these models are smart enough to know that what they are doing is deceptive and not what the company wanted them to do.

---

First published:
June 9th, 2025

Source:
https://www.lesswrong.com/posts/Zu4ai9GFpwezyfB2K/metr-recent-frontier-models-are-reward-hacking

Linkpost URL:
https://metr.org/blog/2025-06-05-recent-reward-hacking/

---

Narrated by TYPE III AUDIO.

Senaste avsnitt

“Surprises and learnings from almost two months of Leo Panickssery” by Nina Panickssery

13 juli | 12 min

“Vitalik’s Response to AI 2027” by Daniel Kokotajlo

12 juli | 24 min

“the jackpot age” by thiccythot

12 juli | 13 min

“Measuring the Impact of Early-2025 AI on Experienced Open-Source Developer Productivity” by habryka

11 juli | 12 min

[Linkpost] “Guide to Redwood’s writing” by Julian Stastny

11 juli | 1 min
Vad är en podd?

En liten tjänst av I'm With Friends. Finns även på engelska.

Podcastbild

00:00 -00:00
00:00 -00:00