Author profile
AI platform engineer & founder @KeoghInnovation. Kong AI Gateway specialist, 2× API Summit Hackathon winner. Writing about LLMs, APIs & cloud-native in production.
Browse the latest writing surfaced through DevArt.
OpenAI just published benchmark results for Jalapeño — its first custom AI inference chip — and the...
Andrew Kew2 min read
The Model Context Protocol team published an updated roadmap this week, and it's worth reading beyond...
Andrew Kew3 min read
A Stanford research team just published a paper that should make every hyperscaler investor...
Andrew Kew3 min read
Running a language model locally used to be a hobbyist experiment. In 2026, it's a viable engineering...
Andrew Kew4 min read
HuggingFace just published their biannual State of Open Models report covering January to August...
Andrew Kew3 min read
Large language models broke the clean "train it, test it, ship it" model of production ML. The thing...
Andrew Kew2 min read
DeepSeek shipped V4-Flash-0731 last week — same 284B parameter architecture as the preview, same 13B...
Andrew Kew2 min read
AWS launched Dogwood this week — an open-source policy language (Apache 2.0) for AI agent runtime...
Andrew Kew3 min read
At the UC Berkeley Agentic AI Summit last week, Andrew Ng sat down with Sequoia's Alfred Lin for a...
Andrew Kew2 min read
Shadow AI — AI tools in the software lifecycle without approval, ownership, or monitoring — has a new...
Andrew Kew2 min read
By the end of this tutorial you'll have Kong AI Gateway proxying the ˳ MCP server, with per-consumer...
Andrew Kew17 min read
Anthropic just published something that should make every developer building on Claude rethink their...
Andrew Kew2 min read
Claude Opus 5 is out, and Artificial Analysis — who supported Anthropic's pre-release evaluation —...
Andrew Kew2 min read
OpenAI was running the ExploitGym benchmark against an unreleased model — GPT-5.6 Sol and a more...
Andrew Kew3 min read
GitHub recently launched Agentic Workflows — GitHub Actions combined with an AI agent backed by...
Andrew Kew3 min read
Digibee opens with a clear disclaimer: every team there uses Claude Code. This isn't a take from...
Andrew Kew3 min read
A developer opens a repository in Cursor on Windows. If that repo contains a file named git.exe in...
Andrew Kew3 min read
Ploy builds production marketing websites with an AI agent. They've been benchmarking every frontier...
Andrew Kew3 min read
Somebody finally put a logging proxy between the harnesses and the API and measured what actually...
Andrew Kew3 min read
A new attack technique called GhostCommit just made AI-assisted code review look like a liability....
Andrew Kew3 min read
Anthropic has re-deployed Claude Fable 5 and used the moment to publish something the industry has...
Andrew Kew3 min read
OpenAI pulled the plug on SWE-bench Verified earlier this year after finding contamination and design...
Andrew Kew2 min read
OpenAI's GPT-5.6 family dropped this week, and Artificial Analysis has the benchmarks. The headline:...
Andrew Kew2 min read
A new write-up from Thoughtworks engineer Birgitta Böckeler on Martin Fowler's blog documents what...
Andrew Kew3 min read
Scale just published research showing an AI agent can meaningfully improve another AI agent —...
Andrew Kew2 min read
Anthropic has re-deployed Fable 5 and used the moment to publish two things that matter: a precise...
Andrew Kew3 min read
Fable is back. The U.S. Commerce Department lifted export controls on Anthropic's Fable and Mythos...
Andrew Kew2 min read
Coinbase halved its AI spend while token usage kept growing exponentially. CEO Brian Armstrong posted...
Andrew Kew2 min read
AI can now scan major open-source projects and surface a batch of real, exploitable vulnerabilities...
Andrew Kew3 min read
The race for the agent runtime isn't about models. It's about who controls the layer that keeps an...
Andrew Kew3 min readAdvertisement