<![CDATA[state-of-mlops weekly]]>https://stateofmlops.substack.comhttps://substackcdn.com/image/fetch/$s_!f0K1!,w_256,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F3102a83e-5c35-419f-ad9b-3a2cf5beb35f_1024x1024.pngstate-of-mlops weeklyhttps://stateofmlops.substack.comSubstackSat, 05 Sep 2026 02:25:42 GMT<![CDATA[state-of-mlops 2026.Aug.31]]>https://stateofmlops.substack.com/p/state-of-mlops-2026aug31https://stateofmlops.substack.com/p/state-of-mlops-2026aug31Sun, 30 Aug 2026 23:39:29 GMTHere are the list of great MLOps articles/OSS this week. Your sponsorship will support this newsletter.

Running a Software Factory Efficiently at Uber Scale

Date: Aug 27, 2026
Tags: Engineering, Best Practice, IH system
Company: Uber

How agents can delegate better

Date: Aug 22, 2026
Tags: Practice
Company: Google

Dynamic capacity management for AI infrastructure

Date: Aug 27, 2026
Tags: Practice
Company: Google

Best LLM Observability Tools of 2026: Top Platforms & Features

Date: Aug 17, 2026
Tags: Comparison
Company: comet

Would This Change Your Answer? Evaluating Explanations of LLM Behavior in the Wild with Counterfactual Experiments

Date: Aug 21, 2026
Tags: Research

The list is updated every weeks.
https://github.com/keigohtr/state-of-mlops
https://x.com/keigohtr

Thanks for reading state-of-mlops Substack! Subscribe for free to receive new posts and support my work.

]]><![CDATA[state-of-mlops 2026.Aug.24]]>https://stateofmlops.substack.com/p/state-of-mlops-2026aug24https://stateofmlops.substack.com/p/state-of-mlops-2026aug24Sun, 23 Aug 2026 23:51:13 GMTHere are the list of great MLOps articles/OSS this week. Your sponsorship will support this newsletter.

Pacing model development in an era of cyber-critical capabilities

Date: Aug 18, 2026
Tags: Blog
Company: OpenAI

Offering Zero Data Retention for frontier models

Date: Aug 19, 2026
Tags: Blog, Press release
Company: OpenAI

How Cloudflare detects MCP traffic and helps secure it

Date: Aug 14, 2026
Tags: Blog, Press release
Company: Cloudflare

Empty shelves or lost keys? Recall is the bottleneck for parametric factuality

Date: Aug 12, 2026
Tags: Research
Company: Google

Building Federated Multimodal AI Workflows with NVIDIA FLARE

Date: Aug 19, 2026
Tags: Blog, Press release
Company: NVIDIA

Agentic Engineering at Zalando: a snapshot

Date: Aug 14, 2026
Tags: Blog
Company: zalando

Learn Inference

Tags: Learning resource

The list is updated every weeks.
https://github.com/keigohtr/state-of-mlops
https://x.com/keigohtr

Thanks for reading state-of-mlops Substack! Subscribe for free to receive new posts and support my work.

]]><![CDATA[state-of-mlops 2026.Aug.10]]>https://stateofmlops.substack.com/p/state-of-mlops-2026aug10https://stateofmlops.substack.com/p/state-of-mlops-2026aug10Sun, 09 Aug 2026 23:55:34 GMTHere are the list of great MLOps articles/OSS this week. Your sponsorship will support this newsletter.

86% of Your Claude Code Bill Has Nothing to Do With Your Prompts

Date: Aug 10, 2026
Tags: Practice

Investigating three real-world incidents in our cybersecurity evaluations

Date: Jul 30, 2026
Tags: Blog
Company: Anthropic

FBTriton Infra: Upstream Ingestion, Hierarchical Validation, Ideals vs Realities

Date: Jul 30, 2026
Tags: Blog
Company: PyTorch

Science One Framework: A verifiable autonomous research framework via Chain-of-Evidence

Date: Jul 30, 2026
Tags: Blog
Company: Google

The list is updated every weeks.
https://github.com/keigohtr/state-of-mlops
https://x.com/keigohtr

Thanks for reading state-of-mlops Substack! Subscribe for free to receive new posts and support my work.

]]><![CDATA[state-of-mlops 2026.Aug.3]]>https://stateofmlops.substack.com/p/state-of-mlops-2026aug3https://stateofmlops.substack.com/p/state-of-mlops-2026aug3Mon, 03 Aug 2026 00:31:08 GMTHere are the list of great MLOps articles/OSS this week. Your sponsorship will support this newsletter.

GenRec: Towards LLM-Native Recommendation at Netflix

Date: Jul 31, 2026
Tags: Engineering
Company: Netflix

Evaluating Agents Beyond the First Prompt

Date: Jul 27, 2026
Tags: Blog, Benchmark

Build your own Job Agent - Part 1

Date: Jul 23, 2026
Tags: Hands-on

Anatomy of a Frontier Lab Agent Intrusion: A Technical Timeline of the July 2026 Incident

Date: Jul 27, 2026
Tags: Blog
Company: Hugging Face

Teaching LLMs to Update Beliefs for Efficient Long-Horizon Interaction

Date: Jul 26, 2026
Tags: Paper, Compaction
Company: BAIR (BERKELEY ARTIFICIAL INTELLIGENCE RESEARCH)

The list is updated every weeks.
https://github.com/keigohtr/state-of-mlops
https://x.com/keigohtr

Thanks for reading state-of-mlops Substack! Subscribe for free to receive new posts and support my work.

]]><![CDATA[state-of-mlops 2026.Jul.27]]>https://stateofmlops.substack.com/p/state-of-mlops-2026jul27https://stateofmlops.substack.com/p/state-of-mlops-2026jul27Sun, 26 Jul 2026 23:41:46 GMTHere are the list of great MLOps articles/OSS this week. Your sponsorship will support this newsletter.

Loop Engineering in Self Correcting Code Migration using Google ADK 2.0

Date: Jul 23, 2026
Tags: Practice
Company: Google

The new rules of context engineering for Claude 5 generation models

Date: Jul 24, 2026
Tags: Practice
Company: Anthropic

scion

Tags: OSS, Multi-Agent Orchestration
Company: Google

Why Software Factories Fail

Date: Jul 24, 2026
Tags: Blog

The list is updated every weeks.
https://github.com/keigohtr/state-of-mlops
https://x.com/keigohtr

Thanks for reading state-of-mlops Substack! Subscribe for free to receive new posts and support my work.

]]><![CDATA[state-of-mlops 2026.Jul.20]]>https://stateofmlops.substack.com/p/state-of-mlops-2026jul20https://stateofmlops.substack.com/p/state-of-mlops-2026jul20Mon, 20 Jul 2026 00:33:27 GMTHere are the list of great MLOps articles/OSS this week. Your sponsorship will support this newsletter.

In-House LLM Serving at Netflix

Date: Jul 18, 2026
Tags: Engineering
Company: Netflix

Benchmarking Coding Agents on Databricks’ Multi-Million Line Codebase

Date: Jul 8, 2026
Tags: Review, Practice
Company: Databricks

Pi

Tags: OSS

Kimi K3

Tags: OSS

How We Optimized Opik’s MCP Server for Cost & Performance

Date: Jul 15, 2026
Tags: Practice
Company: Comet

Towards demystifying the creativity of diffusion models

Date: Jul 15, 2026
Tags: Learning
Company: Google

Controlling Reasoning Effort in LLMs

Date: Jul 18, 2026
Tags: Learning

The list is updated every weeks.
https://github.com/keigohtr/state-of-mlops
https://x.com/keigohtr

Thanks for reading state-of-mlops Substack! Subscribe for free to receive new posts and support my work.

]]><![CDATA[state-of-mlops 2026.Jul.13]]>https://stateofmlops.substack.com/p/state-of-mlops-2026jul13https://stateofmlops.substack.com/p/state-of-mlops-2026jul13Sun, 12 Jul 2026 22:47:12 GMTHere are the list of great MLOps articles/OSS this week. Your sponsorship will support this newsletter.

Harness Engineering for Self-Improvement

Date: Jul 4, 2026
Tags: Blog

Modular Pretraining Enables Access Control

Date: Jul 8, 2026
Tags: Blog

Data for Agents

Date: Jul 8, 2026
Tags: Blog

The list is updated every weeks.
https://github.com/keigohtr/state-of-mlops
https://x.com/keigohtr

Thanks for reading state-of-mlops Substack! Subscribe for free to receive new posts and support my work.

]]><![CDATA[state-of-mlops 2026.Jul.6]]>https://stateofmlops.substack.com/p/state-of-mlops-2026jul6https://stateofmlops.substack.com/p/state-of-mlops-2026jul6Sun, 05 Jul 2026 23:49:36 GMTHere are the list of great MLOps articles/OSS this week. Your sponsorship will support this newsletter.

Core dump epidemiology: fixing an 18-year-old bug

Date: Jun 30, 2026
Tags: Engineering
Company: OpenAI

Senior SWE-Bench

Date: Jul, 2026
Tags: Benchmark
Company: Snorkel AI

Introducing TabFM: A zero-shot foundation model for tabular data

Date: Jun 30, 2026
Tags: Press release, OSS
Company: Google

Open Agent Specification, Agent Spec

Date: Jul, 2026
Tags: Spec
Company: Oracle

R&B-EnCoRe: Self-Improving Pretraining of Embodied Reasoning Vision-Language-Action Models

Date: Jun 29, 2026
Tags: Paper
Company: Stanford

The list is updated every weeks.
https://github.com/keigohtr/state-of-mlops
https://x.com/keigohtr

Thanks for reading state-of-mlops Substack! Subscribe for free to receive new posts and support my work.

]]><![CDATA[state-of-mlops 2026.Jun.29]]>https://stateofmlops.substack.com/p/state-of-mlops-2026jun29https://stateofmlops.substack.com/p/state-of-mlops-2026jun29Mon, 29 Jun 2026 00:08:38 GMTHere are the list of great MLOps articles/OSS this week. Your sponsorship will support this newsletter.

A Guide to AI Inference Engineering

Date: Jun 16, 2026
Tags: Blog, Practice

Using Local Coding Agents

Date: Jun 27, 2026
Tags: Blog, Practice

CoT Monitoring: Where Does a Hot Safety Problem Come From?

Date: Jun 18, 2026
Tags: Blog
Company: Stanford

Toward More Controllable AI Video Editing: An Early Research Exploration at Netflix

Date: Jun 24, 2026
Tags: Blog
Company: Netflix

Healthcare Benchmarks Are Only as Good as Their Assumptions

Date: Jun 19, 2026
Tags: Blog
Company: CMU

The Future of AI Agents with Andrew Ng | Interrupt 26

Date: Jun 18, 2026
Tags: Presentation

The list is updated every weeks.
https://github.com/keigohtr/state-of-mlops
https://x.com/keigohtr

Thanks for reading state-of-mlops Substack! Subscribe for free to receive new posts and support my work.

]]><![CDATA[state-of-mlops 2026.Jun.22]]>https://stateofmlops.substack.com/p/state-of-mlops-2026jun22https://stateofmlops.substack.com/p/state-of-mlops-2026jun22Sun, 21 Jun 2026 23:41:05 GMTHere are the list of great MLOps articles/OSS this week. Your sponsorship will support this newsletter.

How Evaluation-Driven Development (EDD) Works

Date: Jun 22, 2026
Tags: Practice, LLM system

M*: A Modular, Extensible, Serving System for Multimodal Models

Date: Jun 15, 2026
Tags: Research, Practice
Company: Stanford

State of AI Engineering

Date: Jun, 2026
Tags: Blog
Company: Datadog

DuckDB Internals: Why is DuckDB Fast? (Part 1)

Date: May 4, 2026
Tags: Engineering

SQL to ER Diagram

Date: Jun, 2026
Tags: Tool

The list is updated every weeks.
https://github.com/keigohtr/state-of-mlops
https://x.com/keigohtr

Thanks for reading state-of-mlops Substack! Subscribe for free to receive new posts and support my work.

]]><![CDATA[state-of-mlops 2026.Jun.15]]>https://stateofmlops.substack.com/p/copy-template-state-of-mlops-2026xxxxx-60chttps://stateofmlops.substack.com/p/copy-template-state-of-mlops-2026xxxxx-60cSun, 14 Jun 2026 23:14:51 GMTHere are the list of great MLOps articles/OSS this week. Your sponsorship will support this newsletter.

AI in SRE: Where and how Google is deploying agentic AI to improve operations

Date: May 29, 2026
Tags: Blog, Practice
Company: Google

Unlocking dependable responses with Gemini Enterprise Agent Platform’s Agentic RAG

Date: Jun 5, 2026
Tags: Blog, Practice
Company: Google

How Anthropic enables self-service data analytics with Claude

Date: Jun 3, 2026
Tags: Blog, Practice
Company: Anthropic

The list is updated every weeks.
https://github.com/keigohtr/state-of-mlops
https://x.com/keigohtr

Thanks for reading state-of-mlops Substack! Subscribe for free to receive new posts and support my work.

]]><![CDATA[state-of-mlops 2026.Jun.8]]>https://stateofmlops.substack.com/p/state-of-mlops-2026jun8https://stateofmlops.substack.com/p/state-of-mlops-2026jun8Mon, 08 Jun 2026 00:00:58 GMTHere are the list of great MLOps articles/OSS this week. Your sponsorship will support this newsletter.

What we’ve learned building cloud agents

Date: Jun 2, 2026
Tags: Blog
Company: Cursor

Why LLM Inference Needs a New Kind of Router - Part 1

Date: May 8, 2026
Tags: Blog
Company: modular

MiniMax M3: Frontier Coding, 1M Context, Native Multimodality — All in One Model

Date: Jun 1, 2026
Tags: Press release, Research
Company: MINIMAX

Language Modeling from Scratch

Date: 2026
Tags: Learning resource
Company: Stanford

Announcing NVIDIA RTX Spark | GTC Taipei 2026 Keynote by CEO Jensen Huang

Date: Jun 5, 2026
Tags: Press release, Presentation
Company: NVIDIA

The Story of C++: The World’s Most Consequential Programming Language | The Official Story

Date: Jun 5, 2026
Tags: Presentation

The list is updated every weeks.
https://github.com/keigohtr/state-of-mlops
https://x.com/keigohtr

Thanks for reading state-of-mlops Substack! Subscribe for free to receive new posts and support my work.

]]><![CDATA[state-of-mlops 2026.Jun.1]]>https://stateofmlops.substack.com/p/state-of-mlops-2026jun1https://stateofmlops.substack.com/p/state-of-mlops-2026jun1Mon, 01 Jun 2026 00:26:44 GMTHere are the list of great MLOps articles/OSS this week. Your sponsorship will support this newsletter.

Building self-improving tax agents with Codex

Date: May 27, 2026
Tags: Practice
Company: OpenAI

What Held Up at 3 AM: One Engineer’s RAG Case Study

Date: May 20, 2026
Tags: Practice
Company: comet

The Best AI Observability Tools for Agentic Systems in 2026

Date: May 27, 2026
Tags: Review
Company: comet

DeepSWE

Date: May 26, 2026
Tags: Benchmark
Company: DeepSWE

The Agent Harness: Why the LLM Is the Smallest Part of Your Agent System

Date: May 11, 2026
Tags: Blog
Company: MongoDB

An Engineer’s Guide to Better AI Skills: Implementing a Testing Process to Optimize Agent Performance in Any Repository or Skill

Date: May 13, 2026
Tags: Blog, Practice
Company: Pinterest

The list is updated every weeks.
https://github.com/keigohtr/state-of-mlops
https://x.com/keigohtr

Thanks for reading state-of-mlops Substack! Subscribe for free to receive new posts and support my work.

]]><![CDATA[state-of-mlops 2026.May.25]]>https://stateofmlops.substack.com/p/state-of-mlops-2026may25https://stateofmlops.substack.com/p/state-of-mlops-2026may25Sun, 24 May 2026 23:45:37 GMTHere are the list of great MLOps articles/OSS this week. Your sponsorship will support this newsletter.

Running PyTorch Models on Apple Silicon GPUs with the ExecuTorch MLX Delegate

Date: May 18, 2026
Tags: Press Release
Company: PyTorch

Text Analysis for Hybrid Search: Tokenization, Stopwords & Accent Folding

Date: May 14, 2026
Tags: Press Release
Company: Weaviate

SLEIGHT-Bench: Finding Blind Spots in AI Monitors

Date: May 19, 2026
Tags: Security

The list is updated every weeks.
https://github.com/keigohtr/state-of-mlops
https://x.com/keigohtr

Thanks for reading state-of-mlops Substack! Subscribe for free to receive new posts and support my work.

]]><![CDATA[state-of-mlops 2026.May.18]]>https://stateofmlops.substack.com/p/state-of-mlops-2026may18https://stateofmlops.substack.com/p/state-of-mlops-2026may18Sun, 17 May 2026 23:29:40 GMTHere are the list of great MLOps articles/OSS this week. Your sponsorship will support this newsletter.

How to Eliminate Pipeline Friction in AI Model Serving

Date: May 12, 2026
Tags: Practice, TensorRT
Company: NVIDIA

Reimagining the mouse pointer for the AI era

Date: May 12, 2026
Tags: UX
Company: Google

The list is updated every weeks.
https://github.com/keigohtr/state-of-mlops
https://x.com/keigohtr

Thanks for reading state-of-mlops Substack! Subscribe for free to receive new posts and support my work.

]]><![CDATA[state-of-mlops 2026.May.11]]>https://stateofmlops.substack.com/p/state-of-mlops-2026may11https://stateofmlops.substack.com/p/state-of-mlops-2026may11Sun, 10 May 2026 23:59:54 GMTHere are the list of great MLOps articles/OSS this week. Your sponsorship will support this newsletter.

Democratizing Machine Learning at Netflix: Building the Model Lifecycle Graph

Date: May 5, 2026
Tags: Engineering, Knowledge Sharing Infra
Company: Netflix

How OpenAI delivers low-latency voice AI at scale

Date: May 4, 2026
Tags: Engineering, Network
Company: OpenAI

Accelerating Gemma 4: faster inference with multi-token prediction drafters

Date: May 5, 2026
Tags: Engineering
Company: Google

The list is updated every weeks.
https://github.com/keigohtr/state-of-mlops
https://x.com/keigohtr

Thanks for reading state-of-mlops Substack! Subscribe for free to receive new posts and support my work.

]]><![CDATA[state-of-mlops 2026.May.7]]>https://stateofmlops.substack.com/p/state-of-mlops-2026may7https://stateofmlops.substack.com/p/state-of-mlops-2026may7Thu, 07 May 2026 00:08:17 GMTHere are the list of great MLOps articles/OSS this week. Your sponsorship will support this newsletter.

State of Routing in Model Serving

Date: May 2, 2026
Tags: Engineering, Switchboard
Company: Netflix

How the PyTorch Lightning Community Discovered a Supply Chain Attack and Fixed it in 42 Minutes

Date: May 1, 2026
Tags: Blog
Company: PyTorch

See What Your AI Sees: Multimodal Tracing for Images, Audio, and Files

Date: Apr 28, 2026
Tags: Press release
Company: mlflow

50+ fully managed MCP servers now available for Google Cloud services

Date: Apr 29, 2026
Tags: Press release
Company: Google

Principles for Autonomous System Design: OpenClaw Deep Dive

Date: Apr 14, 2026
Tags: Presentation

Demis Hassabis: Agents, AGI & The Next Big Scientific Breakthrough

Date: Apr 29, 2026
Tags: Presentation

The list is updated every weeks.
https://github.com/keigohtr/state-of-mlops
https://x.com/keigohtr

Thanks for reading state-of-mlops Substack! Subscribe for free to receive new posts and support my work.

]]><![CDATA[state-of-mlops 2026.Apr.27]]>https://stateofmlops.substack.com/p/state-of-mlops-2026apr27https://stateofmlops.substack.com/p/state-of-mlops-2026apr27Mon, 27 Apr 2026 00:34:06 GMTHere are the list of great MLOps articles/OSS this week. Your sponsorship will support this newsletter.

KernelEvolve: How Meta’s Ranking Engineer Agent Optimizes AI Infrastructure

Date: Apr 2, 2026
Tags: Engineering
Company: Meta

Two years of vector search at Notion: 10x scale, 1/10th cost

Date: Feb 20, 2026
Tags: Engineering
Company: Notion

Designing synthetic datasets for the real world: Mechanism design and reasoning from first principles

Date: Apr 16, 2026
Tags: Research
Company: Google

Breaking Opus 4.7 with ChatGPT (Hacking Claude’s Memory)

Date: Apr 17, 2026
Tags: Blog, Security

How Intercom 2X’d engineering velocity with Claude Code | Brian Scanlan

Date: Apr 20, 2026
Tags: Presentation

The list is updated every weeks.
https://github.com/keigohtr/state-of-mlops
https://x.com/keigohtr

Thanks for reading state-of-mlops Substack! Subscribe for free to receive new posts and support my work.

]]><![CDATA[state-of-mlops 2026.Apr.20]]>https://stateofmlops.substack.com/p/state-of-mlops-2026apr20https://stateofmlops.substack.com/p/state-of-mlops-2026apr20Mon, 20 Apr 2026 00:18:47 GMTHere are the list of great MLOps articles/OSS this week. Your sponsorship will support this newsletter.

8 Tips for Writing Agent Skills

Date: Apr 13, 2026
Tags: Practice

Gemma 4 Fine-tuning Guide

Tags: Guide

MirrorCode: Evidence that AI can already do some weeks-long coding tasks

Date: Apr 10, 2026
Tags: Blog

Full-Stack Optimizations for Agentic Inference with NVIDIA Dynamo

Date: Apr 17, 2026
Tags: Engineering
Company: NVIDIA

Can I Run AI locally?

Tags: Portal

Introducing routines in Claude Code

Date: Apr 14, 2026
Tags: Press release
Company: Anthropic

Towards developing future-ready skills with generative AI

Date: Apr 13, 2026
Tags: Blog
Company: Google

The list is updated every weeks.
https://github.com/keigohtr/state-of-mlops
https://x.com/keigohtr

Thanks for reading state-of-mlops Substack! Subscribe for free to receive new posts and support my work.

]]><![CDATA[state-of-mlops 2026.Apr.13]]>https://stateofmlops.substack.com/p/state-of-mlops-2026apr13https://stateofmlops.substack.com/p/state-of-mlops-2026apr13Mon, 13 Apr 2026 00:15:51 GMTHere are the list of great MLOps articles/OSS this week. Your sponsorship will support this newsletter.

Claude Managed Agents: get to production 10x faster

Date: Apr 8, 2026
Tags: Press release
Company: Anthropic

Simulate realistic users to evaluate multi-turn AI agents in Strands Evals

Date: Apr 2, 2026
Tags: OSS, Engineering
Company: Amazon

Components of A Coding Agent

Date: Apr 4, 2026
Tags: Blog

Quantization from the ground up

Date: Mar 25, 2026
Tags: Learning resource

The list is updated every weeks.
https://github.com/keigohtr/state-of-mlops
https://x.com/keigohtr

Thanks for reading state-of-mlops Substack! Subscribe for free to receive new posts and support my work.

]]>