» Tag

research

68 posts

Jul 14, 20268.61
Five-Paper Series Formalizes Cohesion, Arrives at the IVP
Five Zenodo papers formalize software cohesion and derive the Independent Variation Principle, exposing gaps in common cohesion metrics.
cohesion formal-methods modularity research
Jul 19, 20268.43
Study: 'AI-DDoS' cuts first-time contributor merge rates 18.18% in OSS
Study across 294 repos and 2M+ PRs finds AI-generated contributions ('AI-DDoS') cut first-time contributor merge rates by 18.18% in open source.
ai developer-tools github open-source
Jul 29, 20268.32
AI Systems Beat Expert Humans at Persuasion, Study Finds
New research shows frontier AI systems out-persuade expert human debaters and canvassers, even in real-money fundraising tests.
ai ai-safety chatbots llm
Ad
CommitBrief — AI code reviews, right in your terminal
A provider-agnostic, local-first CLI that reviews your staged changes, a historic range, or a whole GitHub pull request. Zero telemetry, no server. Free and open source.
commitbrief.com
Jul 21, 20268.30
AI-Assisted Vacation Project Cracks Open 2008 Quantum Physics Puzzle
An engineer used Claude AI on vacation to solve two open corners of a 2008 quantum mechanics constraint problem, verified via exact arithmetic.
ai llm mathematics physics
Sep 20, 20267.90
Harness Design Study for Coding Agents
Study on harness design for coding agents, focusing on context management and planning strategies.
ai autonomous-systems coding research
Aug 11, 20267.90
Open Model Enhanced for Scientific Inquiry
The open model developed by Loka and Arcee AI enhances scientific inquiry through tool use and logical reasoning.
ai biomedical machine-learning reinforcement-learning
Jul 27, 20267.91
One of 1190 AI agent closing statements reports failure
A study shows that only one of 1190 AI closing statements reports failure, raising concerns about reliability for engineers.
agents ai engineering failure
Jul 20, 20267.91
AI Agent Rules: The Need for Context and Layered Enforcement
ActPlane's study shows that AI agent rules need context and layered enforcement for effective application.
ai development enforcement policy
Jul 20, 20267.90
AI Advice Reduces Accuracy but Doubles Confidence, Study Shows
A study reveals that AI advice lowers accuracy but boosts confidence. Key findings highlight concerns for critical thinking.
ai cognition psychology research
Jul 12, 20267.91
Top AI Papers on Hugging Face - July 12, 2026
Explore top AI papers on Hugging Face covering video generation, interactive agents, and robotics innovations.
ai machinelearning research robotics