phd candidate @oiioxford @uniofoxford | research scientist @AISecurityInst | AI, social data science, persuasion with language models
Oxford
- Tweets 238
- Following 880
- Followers 1,460
- Likes 524
Pinned Tweet
New w/ @AISecurityInst & @UniofOxford:
Frontier AI can now out-persuade expert humans in conversation - incl. world-champ debaters and professional canvassers.
This held even when humans chose their topics, prepared in advance, and competed for £1,000 prizes 🧵
59
242
987
218,626
Kobi Hackenburg retweeted
🚨Published in @Nature: We show how AI can simulate human behavior to predict experimental results as accurately as experts
Our work has many implications for AI safety. For example, simulators can be used to aid harmful manipulation, and current safeguards do not prevent this🧵
4
38
158
23,862
Kobi Hackenburg retweeted
🚨🚨New paper in @Nature with @AshuAshok, @lukebeehewitt & @ghezae_isaias 🚨🚨
Can LLMs predict results of social science experiments?
Across 70 preregistered studies, we find strong correspondence (r=.85) between LLM-predicted and observed effects.
doi.org/10.1038/s41586-026-1… 🧵
16
148
457
70,854
Kobi Hackenburg retweeted
See for exciting new results on AI “super-persuasion” 👇
Excellent work by all involved, especially Kobi, who I increasingly suspect is an ensemble of humans/aliens living inside a human meat suit such is his magnificent output.
New w/ @AISecurityInst & @UniofOxford:
Frontier AI can now out-persuade expert humans in conversation - incl. world-champ debaters and professional canvassers.
This held even when humans chose their topics, prepared in advance, and competed for £1,000 prizes 🧵
1
2
8
1,624
New w/ @AISecurityInst & @UniofOxford:
Frontier AI can now out-persuade expert humans in conversation - incl. world-champ debaters and professional canvassers.
This held even when humans chose their topics, prepared in advance, and competed for £1,000 prizes 🧵
59
242
987
218,626
Regardless of these uncertainties, we hope this work can be a starting place for discussion (and further research!) on the impacts these persuasive systems could have on society in the near future
1
19
2,876
This was a big effort - huge thanks to my collaborators @acarolinewagner @lukebeehewitt @Ben_Tappin @hannahrosekirk @HelenMargetts @summerfieldlab, and to many at @AISecurityInst for making it possible 🙏
Comments and feedback welcome!
Paper: arxiv.org/abs/2606.16475
3
66
3,023
