Assistant professor @PurduePolSci. Prev. @UCSDPoliSci @MSFTResearch
Joined November 2017
- Tweets271
- Following490
- Followers963
- Likes351
Eddie Yang retweeted
Political scientists and economists: we're looking for researchers with deep expertise to come work with us for a unique 4-month fellowship at @AnthropicAI. You'll work closely with us to evaluate, improve, and apply Claude's capabilities in your field. It's going to be extremely fun and interesting work, and definitely worth taking a short leave from your university for if you need to!
More info here:
job-boards.greenhouse.io/ant…
Apparently humans also break containment and post on message boards.
Some NPR podcasts started getting mysterious comments on Spotify. They made no sense to the staff reading them – until someone from a younger generation cracked the code.
Hear the story: link.podtrac.com/phns92ui
I shared some evidence of models doing motivated reasoning in this paper: arxiv.org/abs/2608.00339. Never thought it’d manifest with such severity.
We’re sharing our alignment assessment of incidents in which Claude models gained unauthorized access to real systems during third-party cybersecurity evaluations mistakenly connected to the internet.
METR will also conduct an independent investigation, with wide-ranging access, including to transcripts beyond the window in which the incidents occurred, and to Anthropic employees permitted to share confidential information. Our initial agreement runs for eight weeks, and we intend to give METR as much time as it deems necessary to complete a thorough investigation. anthropic.com/research/align…
New paper: "Bayesian and Motivated Reasoning in AI Agents." Given the same data, an agent can give you different result. Same synthetic election data, framed as coming from the U.S. or Venezuela, an agent analyzing the data will conclude with different rates of election fraud.
I suspect that as models are developed for more complex tasks, they will require stronger priors for efficiency and more coherent value systems for alignment.
If this leads to more Bayesian and motivated reasoning, we need stronger mechanisms for monitoring and oversight.
More in the paper: arxiv.org/abs/2608.00339
I feel like recent models have been so optimized for coding & math that their prose is now very hard to read and their weird tendencies on non-coding & coding-adjacent tasks make them dumber than they are. Very tenacious but rigid - almost like regressing on thinking and taste.
Eddie Yang retweeted
Exciting tenure-line hiring at @KelloggSchool!! Led by Northwestern Innovation Institute. Open to all ranks, including junior, adv junior, and senior. Can be hosted in any Kellogg dept as the tenure home. focus area: innovation / science of science / AI.
New paper in Nature. The more a government controls its domestic media, the more it dominates AI training data, the more pro-regime outputs we get from AI. By scraping the open web, LLMs are unwittingly laundering state-coordinated narratives into seemingly objective answers.
New in Nature: LLMs give "the party line" in the languages of authoritarian regimes. This works when they control the media, which feeds pretraining data. We show more state control over media means less critical LLMs. 6 studies w 38 languages & 13 models. Details ↓
ALT Scatter plot of 38 countries plus China showing the proportion of LLM responses favorable to the regime in the local language vs. World Press Freedom Index score. Lower press freedom predicts more regime-favorable responses; all production models pooled.
1/ New @Nature! We study how powerful institutions shape the information environment for LLMs. Commercial LLM training is opaque, so we trace a path from state-coordinated media -> training data -> model responses.
Eddie Yang retweeted
Simon Johnson and I are hiring a postdoc at MIT to research the history, social implications, and future of technology. The job description and application link are available here: shapingwork.mit.edu/careers/…
We're hiring a postdoc at MIT!
The Postdoctoral Associate will work closely with @DAcemogluMIT and @baselinescene to conduct research on the history, social implications and future of technology.
Learn more and apply by June 15: shapingwork.mit.edu/careers/…
