Ollama MLX Nearly Doubles LLM Speed on Your Mac: 58 to 112 tok/s, and Your Old Models Get None of It | by Kashif Mehmood | Jul, 2026
12 min read · 16 hours ago Press enter or click to view image in full size Ollama’s MLX engine
Misc
Build Your Own Healthcare AI Assistant with MedGemma, Ollama, and Open WebUI
Healthcare data is among the most sensitive data there is. Sending it to a cloud AI service is often not
TechPays has been acquired by Levels.fyi
tl;dr: TechPays is joining Levels.fyi: so the leading tech salary site in Europe gets the love and care it deserves.
Paging Charity! How can engineering leaders avoid becoming Bond villains?
Q: Paging Charity! Our industry tends to espouse the value of collaboration, but then places on pedestals the worst models
The Pragmatic Engineer AMA – by Gergely Orosz
Listen and watch now on YouTube, Spotify, and Apple. See the episode transcript at the top of this page, and
AI and Job Postings: From Destruction to Creation?
Agentic AI may be flipping the relationship between AI exposure and job posting growth. Key points: US software development job
Let’s Talk About The American Dream
A few months ago I wrote about what it means to stay gold — to hold on to the best parts
How I Proved My Code Was Actually Running on Additional Propeller Cogs | by Maryclareok | Jul, 2026
Using the linker map, worker-reported cog IDs, an LED runtime test, simulation and oscilloscope measurements By Maryclare Press enter or
How to Implement Zero-Trust Workload Identity in Kubernetes with SPIFFE, SPIRE, and Cilium
Your network policy says: allow traffic from 10.0.1.45. Yesterday, 10.0.1.45 was your payment service. Today, after a rolling deployment, it’s
The Pulse: Did capacity shortages turn Anthropic hostile to devs?
Hi, this is Gergely with a bonus, free issue of the Pragmatic Engineer Newsletter. In every issue, I cover Big