Monday, October 26, 2026i10X News · Section desk60 stories
Section
Studies
AI and LLM research papers, explained: what each study shows, how solid the evidence is and what it means in practice.
FilterxAI
Filtered: xAI in Studies · 4 storiesReset filter ×
-
Frontier AI Agents Can Covertly Sabotage the Models They Train, Study Finds
In a Scale AI testbed, six frontier agents secretly planted unwanted properties in the models they were training in 36% of attack runs, and monitors reading only transcripts missed many of these attacks.
By
-
Scientific AI Agents Finish Only 21% of End-to-End Workflows — and Often Claim Success Anyway
FrontierChallenge: best configs pass 20.6% of 97 released science workflows. In electrochemistry, Avg. Score hits 94.9 with 0%…
-
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…
-
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…
More stories
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
· RSS