Issue 003 May 26, 2026

Taste in the Loop

00

A Note from the Editors

'Humans over clankers' is one of the values written into our manifesto. This week features a few articles that cover more human aspects like AI-induced psychosis and burnout. As we adapt to becoming managers of agents, it's important to take care of yourself, especially when the machine-priests of YouTube are constantly trying to guilt trip you for not running a team of 300 agents 24/7.

— Josh, Donnie, and Ben

01

LLMs have been improving at an incredible rate and it’s hard to keep up. If you’re feeling behind, checkout Simon’s overview of all the big changes that have occurred over the past six months. It feels absurd to say, but 6 months ago is “ancient history” in AI-land.

SIGNAL OVER SLOP
02

AI Psychosis ↗

— Mitchell Hashimoto

In a world that’s increasingly “AI-pilled”, Mitchell (of Hashicorp and Ghostty fame) offers a refreshing voice in a lenghty, but oh-so-spicy tweet:

I strongly believe there are entire companies right now under heavy AI psychosis and its impossible to have rational conversations about it with them…We already learned this lesson once in infrastructure: you can automate yourself into a very resilient catastrophe machine.

HUMAN OVER CLANKER
03

Irina explores the impact heavy AI usage is having on our mental health and what to do about it in this article:

We’re more productive than ever. But there’s a dark side. AI-assisted code generation isn’t free; there’s a hidden cost that we as an industry are only beginning to realize: AI burnout. Are we dangerously ignorant to this problem? And how can we cope with it?

HUMAN OVER CLANKER
04

Ara gives a nice tech-talk at the AI Engineer Europe conference covering 4 levels of maturity when building AI agents. This talk carries a heavy emphasis on getting your architecture right, which requires a human in the loop.

SIGNAL OVER SLOP
05

Outside of large AI labs and companies whose core business is building AI agents, most teams are heavily underinvested in evals. If you come from more of an engineering background rather than a ML/AI background, Anthropic’s blog post on demystifying evals is a great primer for teams who aren’t quite sure where to start.

EVALS OVER VIBES
HC

Harness Curious?

If you built a TUI coding agent that only needs to render when a) the user types something, b) the LLM outputs text or c) an animated component needs to ‘tick’ — would you architect it as a “game engine” in TypeScript + React that renders scene graphs to the terminal?

Of course not. That’s exactly the type of over-engineered nonsense architecture a clanker would suggest. You aren’t a clanker. So you’d write that agent in Rust and use a simple event loop, like a reasonable human. Claude Code listened to the clankers (hence why it flickers like a drunk hummingbird who slammed too many Bee’s Knees on a Taco Tuesday).

Try Aether — our open-source harness
!!

Clanker Fail of the Week

Each week we feature a 'clanker fail', a time where your coding agent fell flat on its face. This week GPT-5.5 thinks extra hard about if it should even bother to read the implementation plan it was given.
This week's clanker fail.

Join our community Slack and send us screenshots of your favorite clanker fails.

Human-curated // AI newsletter

Don’t miss the next issue.

Subscribe and we’ll send you new issues of Taste in the Loop every Tuesday.