Blog Posts | Joshua Berkowitz

23 Articles

2025 × LLM ×

Oh My OpenCode: The Open Source Plugin Turning Your Terminal Into an AI Development Team

Your AI peer is heretonot just run commands but orchestrate an entire development team of AI agents, each with specialized skills, working in parallel on your codebase. This is not science fiction. Th...

AI Claude Developer Tools GPT LLM Multi-Agent OpenCode Open Source Terminal TypeScript

Jan 6, 2026

0 3740

Github Repos

Anthropic Skills: Teaching AI Agents How to Work Like Experts

Imagine onboarding a brilliant new colleague who already has vast general knowledge but lacks the specific procedures, templates, and organizational quirks unique to your work. You would not rewrite t...

Agent Skills AI Anthropic Claude LLM Machine Learning Open Source

Dec 19, 2025

0 3179

Github Repos

Docker cagent: The Open-Source Multi-Agent AI Runtime

In the rapidly evolving landscape of AI, building and deploying AI agents has often required navigating a maze of complex frameworks, managing multiple API integrations, and wrestling with configurati...

AI Agents Artificial Intelligence Developer Tools DevOps Docker Enterprise AI Go LLM Marketing Automation MCP Multi-Agent Systems Open Source

Dec 16, 2025

0 1650

Github Repos

How Align Evals Is Updating LLM Evaluator Alignment

Ensuring large language model (LLM) applications truly meet user needs is challenging. Automated evaluation tools often miss the mark, producing scores that don't always align with real human judgment...

AI evaluation alignment developer tools evaluation LangChain LLM product update prompt engineering

Dec 6, 2025

0 781

News

Wayfinding AI: Transforming Health Conversations Through Context-Seeking

Online health information seeking has become ubiquitous, with 58.5% of US adults using the internet for health and medical questions . However, this widespread access comes with significant chall...

AI Context-Seeking Conversational AI Google Research Health LLM Medical AI User Experience

Nov 16, 2025

0 1870

Papers

DeepAnalyze-8B: The First Agentic LLM for Autonomous Data Science

In October 2025, the Database & Intelligent Information Retrieval Laboratory (DBIIR) at Renmin University of China released DeepAnalyze-8B , marking a significant milestone in the evolution of artific...

Agentic AI AI Autonomous AI Data Science LLM Machine Learning Open Source Python

Nov 13, 2025

0 4939

Github Repos

Building the Future of AI Agents: Inside Google's Agent Development Kit

When Google released the Agent Development Kit in early 2025, they weren't just offering another framework for building AI applications. They were making a bold statement about the future of agentic A...

Agent Development Agent Orchestration AI Agents Gemini Google ADK LLM Machine Learning MCP Multi-Agent Systems OpenTelemetry Production AI Python Software Engineering Vertex AI

Nov 6, 2025

0 22946

Github Repos

How Deeply Do LLMs Internalize Scientific Literature And Citations?

A new study asks a deceptively simple question: when you ask a large language model to suggest references for a paper, does it think like a scientist? The Harvard and CLPS authors probe this by prompt...

Citations LLM Matthew Effect Science of Science

Nov 3, 2025

0 3278

Papers

SLED: Self Logits Evolution Decoding Boosts Factuality Without Retraining

Large language models deliver impressive results across many tasks, yet they still produce incorrect or ungrounded statements, often called hallucinations. A growing body of work explores how to reduc...

Decoding Factuality Inference-Time LLM SLED

Nov 3, 2025

0 3465

Papers

LangChain: Building the Future of Context-Aware AI Applications

In October 2022, a team of engineers released LangChain , a Python framework designed to solve a fundamental challenge in the emerging world of Large Language Models. The question they tackled: how do...

Agent Framework AI Agents Framework LangChain LangGraph LangSmith LLM Machine Learning Open Source Python RAG

Oct 25, 2025

0 14476

Github Repos

ROMA: A Recursive Roadmap for Multi‑Agent Systems

ROMA (Recursive Open Meta-Agents) is an open-source framework from Sentient that turns complex goals into structured, parallelizable work. It does this by recursively decomposing tasks and orchestrati...

agents Agno E2B fastapi goofys LiteLLM LLM multi-agent open source python research

Oct 10, 2025

0 14289

Github Repos

Code World Model: A 32B Agentic Coding LLM Grounded In Execution Traces

This article analyzes a Meta FAIR technical report introducing the Code World Model (CWM), a 32-billion-parameter decoder-only transformer trained to model program execution and agentic software engin...

agents code generation execution traces LLM reinforcement learning software engineering

Oct 7, 2025

0 12111

Papers

1
2

Our latest content

Check out what's new !

See all

Ads

Prompt Maker Image Generator

Struggling with the perfect AI image prompt? My free app helps you generate brilliant ideas and instantly creates an image to match. Go from concept to creation in two clicks!

Most Popular Articles

Check out what the hot topics are!

See all

Every shirt tells a story—and every story

#ClothingForACause