✳flâneur — a map of the web's best reading
If you haven’t recently used Claude Code*, you might not understand where AI is at
davidpreichert.substack.com · 5,989 words · saved by 1 readers
A report on a series of mini machine learning projects, executed with, and mostly by, Claude
If you haven’t recently used Claude Code*, you might not understand where AI is at A report on a series of mini machine learning projects, executed with, and mostly by, Claude David P. Reichert Aug 03, 2026 9 1 3 Share (*) or equivalent agentic coding offerings. Usual disclosure: I work at an AI Lab (Google DeepMind). This post describes work I’ve done in my personal time, and reflects my own opinions. If my ulterior motive is promoting my employer, I’m doing a bad job, because I’ll be using a competitor’s product as the example. So, how big of a deal will AI really be? The future is hard to p
Explore this link on the map →related reading
- When AI builds itself \ Anthropicanthropic.com
- How I Use Claude Code | Philipp Spiessspiess.dev
- Effective harnesses for long-running agents \ Anthropicanthropic.com
- LLM Powered Autonomous Agents | Lil'Loglilianweng.github.io
- The machines are fine. I'm worried about us.ergosphere.blog
- A Guide to Claude Code 2.0 and getting better at using coding agents – sankalp's blogsankalp.bearblog.dev
- Building Effective AI Agents \ Anthropicanthropic.com
- Don’t Outsource Your Thinkingteltam.github.io
- Tracing the thoughts of a large language model \ Anthropicanthropic.com
- Building Effective AI Agents \ Anthropicanthropic.com
- Best practices for Claude Code - Claude Code Docsanthropic.com
- I Let AI Agents Train Their Own Models. Here's What Actually Happened. | Hamza Mostafahamzamostafa.com