thingsithinkithink

thingsithinkithink

Climbing the Ladder of Abstraction

Artificial intelligence

View All
Climbing the Ladder of Abstraction

Climbing the Ladder of Abstraction

I gave a talk at AI Practitioner London on what 'good enough' looks like when you can no longer review every line an AI writes.

The Embedded AI Trio

The Embedded AI Trio

Ethan Mollick on embedding AI builders alongside subject-matter experts - and why, as someone who has been doing this, I have mixed feelings about it.

Like a Ragged Prayer

Like a Ragged Prayer

Some interesting stuff from Alexandra Alter on how AI is disrupting the romance novel industry.

Recent Post

Claude Agent SDK Part 6: Fixing the Bash Bypass and Understanding Permissions

Claude Agent SDK Part 6: Fixing the Bash Bypass and Understanding Permissions

Closing the checkpointing loophole and getting to know the SDK's permission system.

Claude Agent SDK Part 5: Editing Files with Checkpointing

Claude Agent SDK Part 5: Editing Files with Checkpointing

Adding the ability for the agent to create posts that follow my templates, with the ability to recover from mistakes.

Claude Agent SDK Part 4: Implementing Context Profiles

Claude Agent SDK Part 4: Implementing Context Profiles

Building context profiles and usage tracking that works with the SDK's design.

Claude Agent SDK Part 3: The Context Control Problem

Claude Agent SDK Part 3: The Context Control Problem

Discovering the trade-offs between agency and control when building on the Claude Agent SDK.

Claude Agent SDK: Part 2

Claude Agent SDK: Part 2

Continuing to explore Anthropic's Agent SDK - making tool calls more descriptive and learning about Python introspection.

First Impressions of Claude Cowork Mode

First Impressions of Claude Cowork Mode

Trying out Anthropic's new Claude Cowork mode.

← PreviousNext →