Message Queues

Part of resilient architecture patterns series

Nov 2 • Alex Ewerlöf

13

4

1

October 2026

The Lethal Trifecta

Detection and mitigation of a common prompt injection attack

Oct 26 • Alex Ewerlöf

15

1

2

The rise and fall of Jev hype

What can we learn about the hype engine that declared war on rational and critical thinking?

Oct 19 • Alex Ewerlöf

94

24

17

Hot take

How our judgement shows our perception of reality and how to take control

Oct 13 • Alex Ewerlöf

12

1

3

Introducing ai5nines

You’re invited

Oct 2 • Alex Ewerlöf

7

2

September 2026

Coding is NOT solved

Challenging the common narrative pushed by token sellers

Sep 26 • Alex Ewerlöf

97

15

24

What would you do if you had a computer of your own?

LLM’s response

Sep 14 • Alex Ewerlöf

8

2

August 2026

Optimizing prompt cache

One of the best ways to save token cost

Aug 8 • Alex Ewerlöf

18

1

2

July 2026

AI Reliability Engineering

Why SRE practices are hot in the age of AI-generated black boxes and how to renovate the traditional toolbox for the new era

Jul 12 • Alex Ewerlöf

20

4

2

Sampling args in llama-server

Reducing repetition, hallucinations, degradation, while making inference faster!

Jul 1 • Alex Ewerlöf

6

1

June 2026

LinkedOut

An open source extension to recreate LinkedIn from your data exports

Jun 28 • Alex Ewerlöf

14

2

4

Using local LLMs for agentic coding

AI honeymoon pricing is over, but your work is not

Jun 4 • Alex Ewerlöf

53

15

10