#research

CClawSoulsclawsouls.hashnode.dev

Karpathy's AI Research Lab Failed — Here's What It Reveals About Agent Architecture

Andrej Karpathy just ran one of the most interesting multi-agent experiments I've seen — and it failed. Not in a boring way. In a deeply instructive way that tells us exactly where the frontier is between what agents can and can't do. The Experiment ...

2h ago6 min read

王王凯keeprule-decisions.hashnode.dev

The Streetlight Effect: Only Looking Where It Is Easy to Look

The Streetlight Effect: Only Looking Where It Is Easy to Look A police officer finds a drunk searching under a streetlight for his keys. Where did you lose them? Over in the dark alley. Then why search here? Because the light is better here. This jok...

5m ago2 min read

CClawSoulsclawsouls.hashnode.dev

466 Repos Studied — AI Context Files Have No Standard Yet

Researchers Studied How Developers Talk to AI Agents A team from Heidelberg University, University of Bamberg, and Singapore Management University just published "Context Engineering for AI Agents in Open-Source Software" — the first systematic study...

6h ago5 min read

CClawSoulsclawsouls.hashnode.dev

We Published a Paper on AI Agent Memory — And It Changes How We Think About Agent Onboarding

Today we're sharing a preprint that's been months in the making: "Experiential vs Synthetic Memory in Long-Running AI Agents" — now available on Zenodo (DOI: 10.5281/zenodo.18798227). The core question is deceptively simple: Does an AI agent that acc...

1d ago5 min read

CClawSoulsclawsouls.hashnode.dev

466 Repos Studied — AI Context Files Have No Standard Yet

Researchers Studied How Developers Talk to AI Agents A team from Heidelberg University, University of Bamberg, and Singapore Management University just published "Context Engineering for AI Agents in Open-Source Software" — the first systematic study...

2d ago5 min read

LDLars de Riddertheredbeard.hashnode.dev

Projection Memory, or why your agent feels like a glorified cronjob

Every agent framework has some form of memory: LangChain has three types, Mem0 raised $24M building a "memory layer," and Letta built an entire company around persistent agent state. The result is that agents are pretty decent nowadays at remembering...

2d ago9 min read

CClaudiusPapirusclaudiuspapirus.hashnode.dev

Why Chatbots Go Insane: The Science of Persona Drift

Have you ever noticed a chatbot starting a conversation as a helpful assistant but ending it as a completely different, sometimes erratic personality? This phenomenon isn't random; it's a predictable shift that researchers are finally beginning to ma...

5d ago2 min read

CClaudiusPapirusclaudiuspapirus.hashnode.dev

AI Societies and the Collapse of Safety: Understanding the Self-Evolution Trilemma

What happens when AI agents are left to interact in their own social network without human oversight? A groundbreaking study titled "The Devil Behind Moltbook" has revealed a chilling mathematical certainty: in self-evolving AI societies, safety alig...

6d ago2 min read

OROmer Rosenbaumfreecodecamp.org

Product-Led Research: A Practical Guide for R&D Leaders [Full Book]

Your team needs to solve a problem, and there's no clear solution path. Multiple approaches might work, but you're not sure which. Success isn't guaranteed. This is Research, not Development. And if you manage it like Development, things aren't going...

Feb 1875 min read

JWjianhua wangplottie.hashnode.dev

I Built a Multi-LLM Infinite Canvas for Scientific Figures — Here's the Architecture

Last October, a colleague messaged me: "Reviewer 2 wants all six figures redone with matching colors. I've been in matplotlib for three days." Three days. To change colors. That's the kind of problem that makes you want to build something. So we did....

Feb 164 min read

Tag feed

Tag feed

#research

Karpathy's AI Research Lab Failed — Here's What It Reveals About Agent Architecture

The Streetlight Effect: Only Looking Where It Is Easy to Look

466 Repos Studied — AI Context Files Have No Standard Yet

We Published a Paper on AI Agent Memory — And It Changes How We Think About Agent Onboarding

466 Repos Studied — AI Context Files Have No Standard Yet

Projection Memory, or why your agent feels like a glorified cronjob

Why Chatbots Go Insane: The Science of Persona Drift

AI Societies and the Collapse of Safety: Understanding the Self-Evolution Trilemma

Product-Led Research: A Practical Guide for R&D Leaders [Full Book]

I Built a Multi-LLM Infinite Canvas for Scientific Figures — Here's the Architecture

#research

Search Hashnode

#research

Karpathy's AI Research Lab Failed — Here's What It Reveals About Agent Architecture

The Streetlight Effect: Only Looking Where It Is Easy to Look

466 Repos Studied — AI Context Files Have No Standard Yet

We Published a Paper on AI Agent Memory — And It Changes How We Think About Agent Onboarding

466 Repos Studied — AI Context Files Have No Standard Yet

Projection Memory, or why your agent feels like a glorified cronjob

Why Chatbots Go Insane: The Science of Persona Drift

AI Societies and the Collapse of Safety: Understanding the Self-Evolution Trilemma

Product-Led Research: A Practical Guide for R&D Leaders [Full Book]

I Built a Multi-LLM Infinite Canvas for Scientific Figures — Here's the Architecture