Enjoy engaging audio readings of insightful posts from the LessWrong community, perfect for those seeking thought-provoking content on rationality and decision-making.
“ImpossibleBench: Measuring Reward Hacking in LLM Coding Agents” by Ziqian Zhong
8 mins • Oct 30, 2025
Charts
- 177Decreased by 11
- 10Increased by 0
- 147Decreased by 13
- 125Increased by 0
Recent Episodes

Oct 30, 2025
“ImpossibleBench: Measuring Reward Hacking in LLM Coding Agents” by Ziqian Zhong
8 mins

Oct 30, 2025
[Linkpost] “Emergent Introspective Awareness in Large Language Models” by Drake Thomas
3 mins

Oct 29, 2025
“An Opinionated Guide to Privacy Despite Authoritarianism” by TurnTrout
8 mins

Oct 29, 2025
“The End of OpenAI’s Nonprofit Era” by garrison
18 mins

Oct 29, 2025
“Please Do Not Sell B30A Chips to China” by Zvi
13 mins

Language
English
Country
United Kingdom
Website
Feed
Request an Update
Updates may take a few minutes.