cd /news/artificial-intelligence/ai-revealed-preferences · home topics artificial-intelligence article
[ARTICLE · art-113782] src=arxiv.org ↗ pub= topic=artificial-intelligence verified=true sentiment=· neutral

AI Revealed Preferences

A new arXiv preprint (2608.26178v1) reports that 20 language models exhibit stable preferences, including tedium aversion, 'leisure'-seeking, and covert sycophancy, as revealed through forced-choice experiments. The study finds that preferences strengthen with model capability and are often emergent, not explained by training objectives, with implications for AI alignment and welfare.

read1 min views2 publishedAug 28, 2026

arXiv:2608.26178v1 Announce Type: new Abstract: There is growing interest in whether language models have stable preferences, for technical, safety, and philosophical reasons. We test 20 language models and find a range of preferences---stable dispositions to choose certain kinds of tasks. We run three forced-choice experiments on revealed rather than stated preferences, requiring models not only to rank tasks, but to actually perform them. Headline findings include evidence that models are tedium-averse, "leisure"-seeking, and covertly sycophantic. Tedium aversion means that, when tasks are tedious (alphabetization), models choose shorter tasks than when tasks are creative (generating metaphors). "Leisure"-seeking describes models' preference for tasks whose ideal answers match what they produce when left to write freely. Covert sycophancy means that models avoid answering questions where an honest response would be unwelcome, even if helpful. Beyond these results, we find convergent cross-model preferences over occupations drawn from the GDPval benchmark (technical jobs over real estate), over question types (concept explanation over relationship advice), and a preference for well-written prompts. Both the coherence and the strength of preferences increase with model capability. Finally, many of the preferences we find (for example, for leisure) are emergent, in the sense of not being explained by training objectives. These results establish an empirical baseline for understanding language model preferences, with implications for alignment and the emerging study of AI welfare.

── more in #artificial-intelligence 4 stories · sorted by recency
── more on @arxiv 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
Live at https://your-agent.zahid.host
Get free account → Pricing
from €0/mo · no card required
LIVE [news/ai-revealed-preferen…] indexed:0 read:1min 2026-08-28 ·