Thoughts on slowing the fuck down
mariozechner.at · 2,439 words · saved by 4 readers
Thoughts on slowing the fuck down
Thoughts on slowing the fuck down 2026-03-25 The turtle's face is me looking at our industry Table of contents Everything is broken How we should not work with agents and why Compounding booboos with zero learning, no bottlenecks, and delayed pain Merchants of learned complexity Agentic search has low recall How we should work with agents (for now, I think) It's been about a year since coding agents appeared on the scene that could actually build you full projects. There were precursors like Aider and early Cursor, but they were more assistant than agent. The new generation is enticing, and a
saved by
related reading
- Thoughts on slowing the fuck downmariozechner.at
- The Eternal Sloptember | the singularity is nearergeohot.github.io
- Code was our medium for thoughtwattenberger.com
- claude code is not making your product betterethanding.substack.com
- dex (@dexhorthy) on Xx.com
- Towards self-driving codebases · Cursorcursor.com
- Agentic Coding Ascension Notes – Machine Learning (Theory)hunch.net
- Shipping at Inference-Speed | Peter Steinbergersteipete.me
- AI is removing the middle class of software engineeringblog.florianherrengt.com
- Effective harnesses for long-running agents \ Anthropicanthropic.com
- Would you fly on an AI-coded plane | Hackle's bloghacklewayne.com
- Notes on the Software Factorybenedict.dev