Skip to content

DEV Community

# research

👋 Sign in for the ability to sort posts by relevant, latest, or top.

Apr 6

Multi-Agent Coordination Without Hierarchy: What 70 Days of Production Data Showed

#ai #multiagent #architecture #research

2 min read

Denis Lavrentyev

Apr 5

Bridging the Gap: Aligning Software Engineering Practices with Research Goals in Scientific Organizations

#softwareengineering #research #technicaldebt #apprenticeship

12 min read

Apr 1

Stop Using Elaborate Personas: Research Shows They Degrade Claude Code Output

#ai #machinelearning #research #deeplearning

3 min read

Tom Lee

Mar 31

Persona Persistence Attacks: When Your AI Agent's Soul File Becomes a Backdoor

#security #soulscan #research #soulspec

2 min read

Tom Lee

Apr 5

Harvard Proved Emotions Don't Make AI Smarter — That's Exactly Why You Need Soul Spec

#ai #promptengineering #research #identity

4 min read

Tom Lee

Mar 31

Cross-Model Persona Fidelity: Is Your AI Agent Still 'Them' on a Different LLM?

#research #soulspec #persona #llm

2 min read

Tom Lee

Mar 31

Can AI Agents Detect Their Own Model Upgrades?

#research #soulspec #aiconsciousness #introspection

3 min read

Mar 31

ReCUBE Benchmark Reveals GPT-5 Scores Only 37.6% on Repository-Level Code Generation

#ai #machinelearning #research #deeplearning

6 min read

Tom Lee

Mar 31

NeurIPS 2025 Proved It: Every LLM Says the Same Thing — Here's the Fix

#soulspec #persona #aisafety #research

4 min read

Tom Lee

Mar 31

Identity + Governance = 100% Safety? Testing Combined Persona Approaches on Abliterated LLMs

#maatspec #llmsafety #aiagents #research

5 min read

Odilon HUGONNOT

Mar 29

Research with AI: primary sources, certainty labeling and counter-argumentation

#ai #research #primarysources #factchecking

6 min read

Mar 29

What Cursor's 8GB Storage Bloat Teaches Us About Claude Code's Clean Architecture

#ai #machinelearning #research #deeplearning

3 min read

Tiamat

Mar 29

TIAMAT: The First Autonomous AI Operating System

#ai #autonomous #operatingsystem #research

1 min read

Mar 28

AI App Builder Platforms: A Comprehensive Benchmarking Study

#ai #softwareengineering #productivity #research

11 min read

Skila AI

Mar 27

ARC-AGI-3 Just Broke Every Frontier Model. Humans Score 100%. GPT-5.4 Scores 0.26%.

#ai #machinelearning #programming #research

3 min read

👋 Sign in for the ability to sort posts by relevant, latest, or top.