The Journal, page 16
Page 16 of 20 of the Journal archive: AI engineering talk recaps, briefs and build notes, newest first.
- Agentic Search for Context Engineering — Leonie Monigatti, Elastic
- FLUX, Open Research, and the Future of Visual AI — Stephen Batifol, Black Forest Labs
- How Transformers Finally Ate Vision – Isaac Robinson, Roboflow
- Everything You Need To Know About Agent Observability — Danny Gollapalli & Zubin Koticha, Raindrop
- Playground in Prod: Optimising Agents in Production Environments — Samuel Colvin, Pydantic
- Vibe Engineering Effect Apps — Michael Arnaldi, Effectful
- MCP UI: Extending the frontier — Liad Yosef and Ido Salomon, MCP Apps
- Skills at Scale — Nick Nisi and Zack Proser, WorkOS
- The Multi-Agent Architecture That Actually Ships — Luke Alvoeiro, Factory
- Accelerating AI on Edge — Chintan Parikh and Weiyi Wang, Google DeepMind
- Autonomous Coding Strategy - Codex
- Demand-Driven Context: A Methodology for Coherent Knowledge Bases Through Agent Failure
- The Small Model Infrastructure Nobody Built (So We Did) — Filip Makraduli, Superlinked
- Warp terminal provides integrated tools for managing multiple coding agents simultaneously
- Next.js Developers in Florida: Modernizing Outdated Web Apps
- Managing Multiple AI Coding Agents in Warp Terminal: A Complete Guide
- Ralph Loops: Build Dumb AI Loops That Ship — Chris Parsons, Cherrypick
- Skill Issue: How We Used AI to Make Agents Actually Good at Supabase — Pedro Rodrigues, Supabase
- Training an LLM from Scratch, Locally — Angelos Perivolaropoulos, ElevenLabs
- Web Developer Costs in Florida: SaaS Startup Budget Guide
- Context Is the New Code — Patrick Debois, Tessl
- Mergeable by default: Building the context engine to save time and tokens — Peter Werry, Unblocked
- Next.js Developers Are Shipping Bloated Apps (Mine Too)
- TLMs: Tiny LLMs and Agents on Edge Devices with LiteRT-LM — Cormac Brick, Google