Subscribe
Sign in
Home
Technical Leadership
Reliability Engineering
Growth
Cartoons
FAQ
Code
Archive
About
ai
Latest
Top
Discussions
Coding is NOT solved
Challenging the common narrative pushed by token sellers
Sep 26
•
Alex Ewerlöf
71
13
19
What would you do if you had a computer of your own?
LLM’s response
Sep 14
•
Alex Ewerlöf
8
2
Optimizing prompt cache
One of the best ways to save token cost
Aug 8
•
Alex Ewerlöf
17
1
2
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
18
4
2
Sampling args in llama-server
Reducing repetition, hallucinations, degradation, while making inference faster!
Jul 1
•
Alex Ewerlöf
6
1
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
Github Copilot vs Google Antigravity
Why Github gets developers and why it's hard to tell who Antigravity is for
Mar 22
•
Alex Ewerlöf
11
12
2
AI firewall
How to protect your AI application in production against new classes of attacks
Mar 15
•
Alex Ewerlöf
16
1
2
OWASP Top 10 Agents & AI Vulnerabilities (2026 Cheat Sheet)
A pragmatic engineering guide and cheat sheet for the OWASP Top 10 AI, OWASP Top 10 LLM, and OWASP Top 10 Agents vulnerabilities
Mar 10
•
Alex Ewerlöf
20
4
RAG vs SKILL vs MCP vs RLM
Comparing various techniques to make the models more reliable while working around context window limitation
Feb 25
•
Alex Ewerlöf
42
1
6
Multi-Agent System Reliability
4 patterns to tame multi-agent systems for reliability
Feb 19
•
Alex Ewerlöf
28
4
6
This site requires JavaScript to run correctly. Please
turn on JavaScript
or unblock scripts
