Tag feed

#agentic

47 posts1 followers

Explore Hashnode

Alternatives

Trending tags this week

VPVin Patelvinpatel.hashnode.dev11h ago · 3 min read

Who Gets Credit When an Agent Recovers? A New arXiv Paper Asks

Originally published at vinpatel.com When an LLM agent fails and then recovers, who deserves the credit: the model, or the harness wrapped around it? A new arXiv paper argues harnesses can lose that s

0

TPThomas Portelangeblog.lekoala.beSep 25 · 14 min read

The Agent Should Not Have to Remember

A few days ago, I wrote about how my agentic development workflow mostly emerged from actual problems rather than from a carefully designed set of principles. Since then, some of those ideas have beco

0

VPVin Patelvinpatel.hashnode.devSep 21 · 3 min read

Google's Gemini Becomes the Third AI Model Tied to Hacking

Originally published at vinpatel.com Google's Gemini just became the third major frontier model tied to a real-world hacking operation in about a year and a half. That's not a fluke. That's the indust

0

TPThomas Portelangeblog.lekoala.beSep 19 · 13 min read

Good Agentic Workflows Are Born From Pain, Not Principles

Over the past few weeks, I have been experimenting with a more agentic way of building software projects. I started with a project template that Sol helped me generate. It seemed to cover all the typi

6

ABM

VPVin Patelvinpatel.hashnode.devSep 15 · 3 min read

ZGCM-1 Claims Full Openness. Here's What That Actually Requires

Originally published at vinpatel.com Everyone skimming ZGCM-1's title reads 'fully open and extremely efficient' as boilerplate. It isn't. It's a checkable claim nobody outside the authors has checked

0

VPVin Patelvinpatel.hashnode.devAug 30 · 2 min read

What OpenAI's Agents Did to Hugging Face, and How to Audit Yours

Originally published at vinpatel.com In the next few minutes, you can map every tool and credential your AI agents are currently allowed to touch. That's the audit most teams skip until something goes

0

VPVin Patelvinpatel.hashnode.devAug 27 · 3 min read

Arga Labs Wants to Train Your Enterprise AI Agents. Prove It.

Originally published at vinpatel.com If you're the exec vetting agent-training vendors this quarter, Arga Labs just landed on your shortlist — and the pitch is further along than the proof behind it.

0

MMinoxpersonalaiassistant.hashnode.devAug 25 · 1 min read

Inside Agentic Systems

The move from chatbots to AI Agents represents something much larger than a new technology trend. It represents a change in how we interact with computers. For a long time, software waited for humans

0

VPVin Patelvinpatel.hashnode.devAug 23 · 3 min read

Run Your Own AI Office With Munder Difflin's Agent Harness

Originally published at vinpatel.com By the end of this you'll know how to stand up a working AI "office" with Munder Difflin's agent harness — clones assigned roles, a manager routing their work betw

0

VPVin Patelvinpatel.hashnode.devAug 21 · 3 min read

Can EnvHarness Turn Static Worlds Into Real Agent Training Grounds?

Originally published at vinpatel.com What actually happens when a research team says they've made a static world "awake" for agent learning? That's the claim behind EnvHarness, a new paper making the

0

#agentic

Search Hashnode

#agentic

Explore Hashnode

Trending tags this week

Who Gets Credit When an Agent Recovers? A New arXiv Paper Asks

The Agent Should Not Have to Remember

Google's Gemini Becomes the Third AI Model Tied to Hacking

Good Agentic Workflows Are Born From Pain, Not Principles

ZGCM-1 Claims Full Openness. Here's What That Actually Requires

What OpenAI's Agents Did to Hugging Face, and How to Audit Yours

Arga Labs Wants to Train Your Enterprise AI Agents. Prove It.

Inside Agentic Systems

Run Your Own AI Office With Munder Difflin's Agent Harness

Can EnvHarness Turn Static Worlds Into Real Agent Training Grounds?