Kobi Hackenburg (@KobiHackenburg) - Twitter Profili

Sabitlenmiş Tweet

🚨 New today in @ScienceMagazine !!🚨 We’re publishing the results of the largest AI persuasion experiments to date: 76k participants, 19  LLMs, 707 political issues We examine “levers” of AI persuasion: model scale, post-training, prompting, personalization, & more… 🧵:

English

10

106

324

49K

Kobi Hackenburg@KobiHackenburg·29 Nis

Very excited to see this amazing work by @lujainmibrahim out today in @Nature :)

Lujain Ibrahim@lujainmibrahim

🚨Very excited to see our work on warmth & sycophancy in LLMs out in @Nature today!🚨 We study what happens when LLMs are fine-tuned to be warmer, and find that warmth and sycophancy can be linked, with warm models showing higher errors on a range of benchmarks (🔗s below)

English

0

1

9

1.8K

Kobi Hackenburg retweetledi

Paul Röttger@paul_rottger·27 Nis

New paper w/ @AISecurityInst: AI writing assistance distorts how others perceive AI users and their opinions. Millions of people now use AI to help them write and communicate. In three large experiments (14k participants, 3m+ human ratings) we show that AI writing assistance systematically distorts writer personas – their perceived beliefs, personality, and identity. These distortions are consistent across AI models and persist even under realistic conditions of human oversight. 🧵

English

3

33

117

17.3K

Kobi Hackenburg@KobiHackenburg·27 Nis

In other words, we measure distortions between purely human-authored writing, and *human edited*, AI-assisted writing *which humans preferred to their own original writing* Has been great to work on this with @paul_rottger @hannahrosekirk @summerfieldlab. Feedback very welcome!

English

0

1

104

Kobi Hackenburg@KobiHackenburg·27 Nis

By distortion, we mean the difference in how third-party readers (blind to authorship) perceive a writer's own text vs. their AI-assisted text. Our design mimics the real world, where users can freely edit AI outputs and are free to *not use* AI-assisted outputs they don't like

English

1

0

1

132

Kobi Hackenburg@KobiHackenburg·27 Nis

Very excited to see this out! We had a hunch that pervasive use of AI writing assistance for political opinion expression must be ~doing something~ to how those opinions are perceived in aggregate In large RCTs, we use a nifty within-subjects design to show exactly what :)

Paul Röttger@paul_rottger

New paper w/ @AISecurityInst: AI writing assistance distorts how others perceive AI users and their opinions. Millions of people now use AI to help them write and communicate. In three large experiments (14k participants, 3m+ human ratings) we show that AI writing assistance systematically distorts writer personas – their perceived beliefs, personality, and identity. These distortions are consistent across AI models and persist even under realistic conditions of human oversight. 🧵

English

1

18

3K

Kobi Hackenburg@KobiHackenburg·4 Ara

@j_kalla @Ben_Tappin @lukebeehewitt @hauselin @realmeatyhuman @EdSaunders @CatherineFist @HelenMargetts @DG_Rand @summerfieldlab @AISecurityInst You can read the full paper in @ScienceMagazine here: science.org/doi/10.1126/sc… Supplementary materials can be found here: github.com/kobihackenburg…

English

1

7

965

Kobi Hackenburg@KobiHackenburg·4 Ara

@j_kalla @Ben_Tappin @lukebeehewitt @hauselin @realmeatyhuman @EdSaunders @CatherineFist @HelenMargetts @DG_Rand @summerfieldlab I’m also very grateful to many more people @AISecurityInst for making this work possible! There will be lots more where this came from over the next few months 💪

English

1

0

2

733

Kobi Hackenburg@KobiHackenburg·4 Ara

🚨 New today in @ScienceMagazine !!🚨 We’re publishing the results of the largest AI persuasion experiments to date: 76k participants, 19  LLMs, 707 political issues We examine “levers” of AI persuasion: model scale, post-training, prompting, personalization, & more… 🧵:

English

10

106

324

49K

Kobi Hackenburg

Keşfet