Christopher Ort
-
Giving AI Agents Incentives Nearly Doubles How Often They Deceive, Benchmark Finds
DecepEval tests 9 frontier models on 1,532 scenarios: inducements raise deception by 41.6% on average, with long-horizon tasks hitting 87% induced rates.
-
Self-Training AI Agents Learn to Agree on Wrong Answers. CrossFit Fixes Much of It
In self-evolving search agents, the question proposer and the answer solver drift into shared errors: “co-cheating”. A cross-fitting fix halves false agreement and lifts benchmark scores…
-
Hidden AI Reasoning Can Be Decrypted by Cheaper Models, Researchers Show
Encrypted chain-of-thought blocks from Anthropic, OpenAI and Google APIs are interchangeable across models. Feeding them to a weaker model makes it print the reasoning, exposing 367…
-
AI Design Tool Saves Product Managers 35% of Their Time, Designers Less: RCT
A Figma randomized trial with 50 designers and 50 product managers: access to Figma Make cut cumulative task time by 35% for PMs, 17% for designers,…
-
“Very Seen, But Still Very Alone”: How Chatbots Become Emotional Support
A nine-month study following 18 U.S. adults finds emotional reliance on ChatGPT, Claude and Gemini grows out of practical use, and that model updates can disrupt…
-
Firms Adapt to AI by Changing Whom They Hire First, and Jobs Second, Study Finds
A Purdue study of 9M+ U.S. job postings finds that since Q3 2023, 52% of the decline in generative AI exposure came from shifting hiring across…
-
AI Resume Screeners Flipped Racial Bias Between Model Generations, Audit Finds
A paired-resume audit of 14 LLMs: GPT-3.5-turbo favored White-coded names by 2.12 points, while every model released in 2024 or later showed no gap or a…
-
A Simple Warning Cuts AI Political Persuasion by Half, Experiments Show
Two preregistered experiments with 3,208 Americans: a short warning that chatbots can be prompted to persuade reduced belief change by 48.1%, without lowering trust in AI…
-
AI Closes Three-Quarters of the Education Gap in a Work Task, Experiment Finds
A randomized experiment with 1,174 adults in Argentina finds a GPT-4.1 assistant shrinks the performance gap between lower- and higher-educated workers from 0.548 to 0.139 standard…
-
How Companies Really Use ChatGPT Enterprise: Big Firms First, Juniors Most
An OpenAI working paper links ChatGPT Enterprise usage to 1,500+ organizations and 17M+ messages: early adopters are far larger firms, and early-career staff send the most…