How Did One RTX 5090 Run Gemma at ~600 Tok/s?

A new research paper made it possible. A regular developer made it real. The implications are bigger than either piece on its own.

May 18 • Joe Guglielmucci

3

*NEW* Multi Token Prediction Just Made Local Agents Running in vLLM ~3x Faster

A working, easy to follow guide to Multi Token Prediction (MTP) in vLLM, with real benchmarks on Qwen 3.6, Gemma 4, and DeepSeek V4, for anyone serving…

May 12 • Joe Guglielmucci

4

Could GitLab + Coder = End of GitHub?

[1st Hand] field report on the potential partnership Microsoft should worry about

May 12 • Joe Guglielmucci

6

I Went to Manhattan for the AI Agent Conference...

Synthesizing three full days of workshopping and networking in person, so you can learn how $B companies/CEOs use & deploy agents right now (without…

May 7 • Joe Guglielmucci

6

April 2026

What If One Slack Agent Could Live On Your Company's Software...Locally?

NemoClaw's ability to run thousands of agents at scale makes building intelligence locally a necessary business cost

Apr 20 • Joe Guglielmucci

5

1

Why Is Every Fortune 500 Company Sending Their CTO to the Same Hotel in May?

$1500 a ticket

Apr 3 • Joe Guglielmucci

3

2

March 2026

Finding NemoClaw?

Nvidia's release of a trustable, enterprise LvL 'OpenClaw' -- implications are GLOBAL

Mar 11 • Joe Guglielmucci

5

2

The 20-Minute Problem

The solution involves Bitcoin

Mar 9 • Joe Guglielmucci

4

2

February 2026

Is Your Junk Drawer a Supercomputer?

turn obsolete tech into edgenodes that run your new agent

Feb 6 • Joe Guglielmucci

5

2

What is Moltbook? (Deep Dive)

Who or what are these agents?

Feb 4 • Joe Guglielmucci

5

2

Is the Paper Market Rigging the Biggest Wealth Transfer in History?

The Great Silver Unwind, the Warsh Bomb and Crypto on Sale.

Feb 1 • Joe Guglielmucci

3

2

2

January 2026

Non-Slop Market Signals to Monitor in 2026?

My personal real-world market signals to act on this year

Jan 27 • Joe Guglielmucci

4

2