Infrastructure & deployment — Page 10

Why Large? Tiny LMs & Agents on Edge/Robotics

Cormac Brick

Infrastructure & deployment · Voice AI · Robotics

Why MLX

Infrastructure & deployment · Voice AI · Vision & video

Why More Context Makes Your Agent Dumber and What to Do About It

Nupur Sharma

Infrastructure & deployment · Retrieval-augmented generation · Agent engineering

Why We Don’t Need More Data Centers

Dr. Jasper Zhang

Infrastructure & deployment

Why you should care about AI interpretability

Mark Bissell

Infrastructure & deployment · Safety & governance · ML fundamentals

Why your agents need decision traces, not just documents — Zach Blumenfeld, Neo4j

Zach Blumenfeld

Infrastructure & deployment · Observability & reliability · MCP

Why Your AI UX Is Broken (and It's Not the Model's Fault)

Mike Christensen

Infrastructure & deployment · Agent engineering · AI interface design

Writing Principles for Task-Tuned Prompt Engineering

Karina Nguyen

ML fundamentals · Evals · Retrieval-augmented generation

WTF do people use Open Models for??

Eugene Cheah

Infrastructure & deployment · ML fundamentals · Coding agents

You Might Not Need 50 Diffusion Steps

Ziv Ilan

Fine-tuning · Infrastructure & deployment · Generative media

Your agent architecture has a half-life of 6 months

Dan Farrelly

Infrastructure & deployment · Safety & governance · Evals

Your Agent Evolved. Your Evals Didn't.

Ameya Bhatawdekar

Evals · Infrastructure & deployment · Retrieval-augmented generation

Your Agent Failed in Prod. Good Luck Reproducing It.

Tisha Chawla · Susheem Koul

Coding agents · Observability & reliability · Infrastructure & deployment

Your Attention Is the Bottleneck, Not Your Agents — Zack Proser, WorkOS

Zack Proser

Voice AI · MCP · Agent engineering

Your Fine-Tuned Model Is Tech Debt: A 50x ROI House of Cards

Dan Bjornn

Agent engineering · Infrastructure & deployment · AI engineering leadership

Your LLM Deception Monitor Is Broken. The Fix Is in the Training Data - Sachin Kumar, LexisNexis

Sachin Kumar

Observability & reliability · Infrastructure & deployment · Fine-tuning

Your Moat Is Your Data Model

Mike Phipps

Retrieval-augmented generation · Safety & governance · AI engineering leadership

Your realtime AI is ngmi — Sean DuBois (OpenAI), Kwindla Hultman Kramer (Daily)

Sean DuBois · Kwindla Hultman Kramer

Voice AI · MCP · Infrastructure & deployment

Exploits Now Beat Patches: Open Source Security in the AI Era - Patrick Smyth, Chainguard

Patrick Smyth

AI security · Open-source ecosystems · Infrastructure & deployment

Let Anyone at Your Company Ship Internal Apps with AI — Garrett Galow, WorkOS

Garrett Galow

Infrastructure & deployment · Coding agents · Enterprise AI

An AI Future Without the Lock-In — Remy Guercio, Tailscale

Remy Guercio

Infrastructure & deployment · AI platform engineering · Model routing & gateways

The Investor's Edge Lives in Their Head — Anekha Sokhal, Moshi

Anekha Sokhal

AI in finance · Human-in-the-loop validation · Context engineering

How I Learned to Stop Worrying and Love the Sandbox — Matt Brockman, E2B

Matt Brockman

Sandboxes & isolation · Infrastructure & deployment · Observability & reliability

How to Build Financial Agents That Work Across the Web - Jay Sahnan & Arik Bird, Browserbase

Jay Sahnan · Arik Bird

Browser agents & WebMCP · AI in finance · Infrastructure & deployment

The Software Factory: From Bug Report to Production Code — Davis Palmie, Factory

Davis Palmie

Software factories · Developer workflows & testing · Agent engineering

How a Trading Firm Ships New AI Models the Same Day - Noyan Tokgozoglu, Optiver

Noyan Tokgozoglu

AI in finance · AI platform engineering · Infrastructure & deployment

Stop Fine-Tuning to Fix Retrieval Problems — Anant Srivastava

Anant Srivastava

Infrastructure & deployment · Retrieval-augmented generation · Fine-tuning

Every step you take, every call you make: the reliable agent stack — Giselle van Dongen, Restate

Giselle van Dongen

Infrastructure & deployment · Observability & reliability · Human-in-the-loop validation

Large clusters for small models — Daniel Svonava, Superlinked

Daniel Svonava

Infrastructure & deployment

Your AI Agent Has No Nervous System — Matt Gibiec, Dynatrace

Matt Gibiec

Coding agents · Observability & reliability · Developer workflows & testing

Stop Renting Intelligence: The Train-to-Deploy Loop for Specialized AI — Fireworks AI

Jetashree Ravi

Open-weight models · Fine-tuning · Infrastructure & deployment

Taming the AI Hardware Cambrian Explosion — Abdul Dakkak, Modular

Abdul Dakkak

Infrastructure & deployment · GPU programming & kernels · Coding agents

Lessons from Generating 12 Trillion Synthetic Tokens — Bogdan Gaza, DatologyAI

Bogdan Gaza

Fine-tuning · Infrastructure & deployment · Observability & reliability

Why Building an Eval Platform Is Harder Than It Looks — Braintrust

Hossein Niazmandi

Evals · Observability & reliability · Infrastructure & deployment

Fixing the PR Bottleneck — Matt Pocock, AIHero

Matt Pocock

Coding agents · Code review & verification · Developer workflows & testing

Agents That Own Their Inference — Du'an Lightfoot & Khaja Omer, Akamai Technologies

Du’An Lightfoot · Khaja Omer

Local inference · Infrastructure & deployment · Inference

Sandboxes Aren't Optional: 4 Ways to Isolate Coding Agents — Robert Brennan, OpenHands

Robert Brennan

Coding agents · Agent auth · Safety & governance

We Trust AI Agents That Break Every Day - Shy Ruparel, Temporal

Shy Ruparel

Observability & reliability · Agent engineering · Infrastructure & deployment

I Spent Two Years Building the Median — Hariprasad Sudharshan

Hariprasad Sudharshan

Product engineering · Coding agents · Harness engineering

Decoupling the Brain from the Hands: Claude Managed Agents (Part 1 of 4) — Anthropic

Priyanka Phatak · Gabe Cemaj

Agent engineering · Infrastructure & deployment · Agent orchestration

Build Your Own Team of Managed Agents - Jack Wotherspoon, Google DeepMind

Jack Wotherspoon

Agent engineering · Coding agents · Infrastructure & deployment

What Makes Open Models Fast in Production — Sujee Maniyam, Nebius

Dylan Bristot · Sujee Maniyam

Infrastructure & deployment · Fine-tuning · Open-weight models

Build the Right Thing: Product Engineering (Part 2) — Kent C. Dodds, EpicProduct.engineer

Kent C. Dodds

Product engineering · AI interface design · Infrastructure & deployment

From Zero to Leaderboard: Agent Evaluation — Wolfram Ravenwolf, Weights & Biases

Wolfram Ravenwolf

Evals · Coding agents · Observability & reliability

GPU Died. Training Didn't: Self-Healing Training at Scale — Crusoe

Connor Guerrero · Young Jeong · Nikhil Gupta

Infrastructure & deployment · Observability & reliability

Stop Guessing Your vLLM Config: Benchmarking LLMs on Runpod - Chris Vela, Runpod

Chris Vela

Benchmarks · Inference · AI cost & performance

Generation Is Cheap, Review Is Expensive: How to Stop Shipping AI Slop — Gabriel Martinez, G2i

Gabriel Martinez

AI engineering leadership · Code review & verification · Developer productivity

How Revolut Cut AI Coding Costs 90% With Self-Hosted Open Models - David Abitbol, Revolut

David Abitbol

AI cost & performance · Open-weight models · Infrastructure & deployment