Section
Studies – Page 2
AI and LLM research papers, explained: what each study shows, how solid the evidence is and what it means in practice.
FilterOpenAI
More stories
-
AI Agents Guess Wrong at Critical Forks 40% of the Time, Taste-Bench Shows
Taste-Bench’s 502 decision-fork questions: the best frontier model scores only 59.7%. Later evidence is harder, and bigger reasoning budgets do not help — but taste can…
-
AI Agents That Learn the Facts Still Deliver Only 60–70% of the Business Value
FDE-Gym’s 95 real delivery tasks: Claude Opus 5.5 leads at 0.56, but even models that gather 72–85% of key facts deliver just 0.60–0.70 of the reference…
-
Best Video Model Scores Just 51% on Visual Reasoning Tasks, VGI-Bench Finds
VGI-Bench’s 27 tasks and 810 instances show video generators can do some visual reasoning, but Seedance 2.0 tops out at 51%, with almost no self-correction during…
-
Agents’ Last Exam: Even Top Coding Agents Score Under 10% on the Hardest Tier
ALE holds 1,490 expert workflows; the best Codex+GPT-5.5 setup that scores 82% on Terminal-Bench gets under 10% on ALE’s hardest tier and 23.3% overall on ALE-CLI.
-
Most Multi-Agent Setups Violate Safety Rules Mid-Run, Even When the Answer Looks Fine
HarnessAudit-Bench tests 210 tasks across 10 harness configs: more than half of multi-agent setups show trajectory violations that final-answer grading misses.
-
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…
-
“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…
Editor's picks
- Tampered ML: Even the Best AI Models Miss One in Five Planted Research Flaws
- Realistic MCP Faults Halve Agent Quality, and a Bigger Model Doesn’t Help
- Copilot Users Collaborate More, Not Less: Study of 12,000 Employees
- LLM Reviewers Send 76% of Published Top-Journal Papers Back, Yet Miss Most Planted Flaws