Claude Mythos: The System Card

Beyond the cybersecurity headlines - what else is in the 217-page system card?

Apr 9 • Ilia Karelin

9

1

Save Claude Tokens: 16 Tactics for Chat, Code & Cowork

Here’s what each one looks like in practice.

Apr 3 • Ilia Karelin

11

5

March 2026

Claude Computer Use: I Used It to Research This Post

Computer Use is live. Here’s what actually happened when I tried it.

Mar 26 • Ilia Karelin

17

3

2

3 Ways Claude Cowork Dispatch Turns Your Laptop Into a Background Worker

How Claude Dispatch lets you trigger real Cowork sessions from your phone - anywhere, anytime.

Mar 21 • Ilia Karelin

10

3

Prosper Knowledge Repository [Launch]

What’s inside and how to get access

Mar 14 • Ilia Karelin

10

2

1

Claude Chat, Cowork, and Code: The Setup Most People Never Do

With templates, the context files and configuration that make each one actually work and know you.

Mar 5 • Ilia Karelin

21

5

February 2026

Raycast: The App I Use to Connect Claude, Perplexity, and NotebookLM + 35 More Workflows

4 levels of automation - from clipboard history to custom scripts - all set up in 30 minutes. Plus, Notion page with 35 more copy/paste workflows.

Feb 25 • Ilia Karelin

19

1

3

The Post-Prompt Era: Why Systems Beat Prompts (And How to Build One With n8n + Claude)

Here's 3-part system that get you memory, compounding, and integration

Feb 19 • Ilia Karelin and Dheeraj Sharma

20

3

6

Your CLAUDE.md Is Static. Your AI Forgot Everything Again.

How to turn every Claude Code session into a learning loop — so mistakes get documented once and never repeated.

Feb 17 • Ilia Karelin

25

7

5

Claude Code /insights Roasted My Workflow. Here's What I Fixed.

What /insights reveals about your workflow — and the CLAUDE.md rules I added because of it.

Feb 12 • Ilia Karelin

8

1

Opus 4.6 Dropped. The Benchmarks Are the Least Interesting Part

Most people will get 20% of this release’s value. The other 80% is in features everyone’s ignoring.

Feb 7 • Ilia Karelin

38

16

11

January 2026

Your AI Isn't Thinking Alone. It's Running a Committee.

Google research reveals reasoning models simulate internal debates between multiple perspectives - not just longer thinking. Here's how to use that.

Jan 29 • Ilia Karelin

6

2