Blog Posts | Joshua Berkowitz

522 Articles

github ×

SWE-Bench Pro Sets A Higher Bar For AI Coding Agents

As AI coding agents approach human-level performance on existing benchmarks, the research community faces a critical challenge: how do we continue measuring progress when current evaluation suites are...

AI benchmarks coding agents software engineering

Sep 23, 2025

0 87868

Papers

SciVer Puts Multimodal Claim Verification To The Test

Scientific claim verification and reproducibility have emerged as a critical challenges in the era of information abundance and multimodal AI systems. Unlike traditional fact-checking that relies prim...

AI benchmark claim verification multimodal scientific reasoning

Sep 23, 2025

0 6303

Papers

simdjson: JSON Parsing at the Speed of Silicon

JSON parsing is everywhere, but it's rarely fast enough at massive scales. Web servers process millions of API requests daily. Analytics pipelines transform terabytes of log data. Trading systems pars...

c++ data-engineering json performance simd simdjson

Sep 23, 2025

0 15818

Github Repos

Notion MCP Server: A Practical Bridge Between AI Agents and Your Workspace

Notion's open-source Notion MCP Server turns the company's popular productivity platform into a first-class tool provider for AI agents. It implements the Model Context Protocol (MCP), a common langua...

AI Agents Developer Tools LLM MCP Notion OpenAPI TypeScript

Sep 23, 2025

0 60313

Github Repos

Defeating Nondeterminism In LLM Inference

Reproducible outputs at temperature 0 should be straightforward in principle, the sampler always picks the highest probability token, yet production LLM endpoints still produce different completions f...

attention batch-invariance determinism gpu-kernels llm-inference

Sep 23, 2025

0 47124

Papers

ONNX Runtime : Inference Runtime for Portability, Performance, and Scale

Deploying machine learning models efficiently is as important as training them. ONNX Runtime , an open-source accelerator from Microsoft, promises fast, portable inference across operating systems and...

deployment inference ONNX runtime TensorFlow Serving Triton

Sep 23, 2025

0 64988

Github Repos

Turning Agents Into Sharable Software: Inside Docker’s cagent

A small utility that feels like a platform: Docker's cagent turns AI agents into sharable, runnable software. Teams often build a clever assistant or a small cluster of cooperating agents. Then real-w...

AI agents Docker Go MCP Open Source Reproducibility

Sep 23, 2025

0 9130

Github Repos

AutoGen: Microsoft's Agent Framework, Reimagined for Multi-Agent Workflows

AutoGen is Microsoft's open-source framework for building AI agents that can collaborate, call tools, and even form teams - without making developers choose between speed and control. Housed in the mi...

actor model agent collaboration agent orchestration AI framework AutoGen autogen-core AutoGen Studio MCP integration Microsoft multi-agent systems RoutedAgent

Sep 22, 2025

0 117128

Github Repos

PosterGen: Academic Poster Creation with Multi-Agent AI

Creating compelling conference posters is a challenge for any researcher. You have to accurately and compelling decide which content and how it will be presented. After months of rigorous research, wr...

academic tools artificial intelligence design automation machine learning multi-agent systems poster design research tools scientific communication

Sep 22, 2025

0 4026

Github Repos

Docker's Cagent Makes Building and Sharing AI Agents Effortless

Docker’s open-source project, Cagent , lets users define AI agent behaviors, tools, and personas in a single YAML file. By removing the pain of dependency management and code complexity, Cagent shifts...

AI agents developer tools Docker MCP toolkit no-code open source workflow automation YAML

Sep 22, 2025

0 11187

News

Paper2Agent: Transforming Research Papers into Interactive AI Agents

Research papers are traditionally require readers and reviewers to interpret code, methods, and results independently. Paper2Agent aims to transform published research into interactive AI agents allow...

AgentScope AI agents AutoGen Azure AI Agents Claude Code Code2MCP computational biology LangGraph MCP NotebookLM OpenAI Assistants OpenDevin open source reproducibility Stanford tutorial extraction

Sep 21, 2025

0 13200

Github Repos

How to Choose the Right Google AI Developer Tool for Your Workflow

AI development is advancing fast, and Google’s portfolio of developer tools is evolving to keep pace. With so many options now available, selecting the right tool for your workflow can feel overwhelmi...

AI development AI tools Code Assist developer workflow Firebase Studio Gemini Google Cloud Jules

Sep 21, 2025

0 2453

News

19
20
21
22
23

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