Joined February 2012
- Tweets 8,378
- Following 688
- Followers 729
- Likes 17,085
1,009 Photos and videos
Pinned Tweet
May 20
What I am currently working on…
1. I trade 📈 10 years, stocks, crypto, options, futures. Disciplined risk/reward. I publish weekly education and setups with a macro read in my newsletter Market Insights & Trading Trends.
2. I build private AI operating systems for
businesses. Cloud or locally hosted. Prefer local because it is fully owned, no dependencies or limits. The agents can actually run workflows 24/7, not just answer questions.
If you are interested in one of those two things right now 👇🏽
If it's trading:
→ ktusing34.substack.com
If it's AI for your business:
→ ai.kyletusing.com
If it's both, you're in the right place just give me a follow 👊🏽
2
2
189
Jun 13
Anthropic pulled Claude Fable 5 because it’s a national security threat. Too powerful for non-US citizens to access...
Models are getting that capable.
This is exactly why I’ve been preaching local, sovereign AI infrastructure.
If your business is going to rely on it, own your models.
Own your stack.
Own your advantage.
1
96
Jun 13
You can read about my 6 Hermes agent build, self-healing, plus a clients build that’s in phase 2-3. All running on a Gigabyte DGX spark GB10 box, $0 API cost.
linkedin.com/posts/kyle-tusi…
109
Jun 6
Palantir told the US government that ungoverned LLMs are dangerous.They’re right.
The fix is owning the layer where your data, models, and governance actually meet. Most businesses can’t afford Palantir, but this architecture isn’t exclusive to them anymore.
Jun 4
“Pointing an LLM at hundreds of disconnected, ungoverned databases gets you a system that hallucinates, is insecure, and unauditable. For something as consequential as our nation’s agricultural data, that is not just useless — it’s dangerous. The Ontology has been the key to delivering AI-enabled technology to every farmer in the country.”
At AIPCon 10, the USDA demonstrates how the Ontology now underpins national food supply security.
57
Kyle Tusing retweeted
Jun 2
That’s impressive ! Keep going . With such effort it is not even a question that you will become next ai billionaire
1
1
1
69
Jun 1
Update to this coming soon! Going to talk about the @GIGABYTEUSA AI Top Atom GB10 computer running Qwen and @nvidia Nemotron!
89
May 30
Posting screenshots of your AI agents is one thing, posting the learnings from when it all collapses at scale is hopefully more valuable.
I’ve broken my Hermes/OpenClaw stack over 30 times. Here’s 11 of them, each failure the fix so you don’t have to learn them the hard way.
69
May 25
If you are running OpenClaw, Hermes, etc.
Either use this skill or have your agent check all of your skills and implement everything mentioned below.
I haven’t tried @steipete exact skill but I have had all of my skills optimized for token usage and context control.
May 25
Folks: when you write skills, ask your agent to be token efficient, relax grammer. I see too many skills that write books in the skill description, and all that crap is loaded into every context.
I wrote a skill that finds the worst offenders. github.com/steipete/agent-sc…
1
86
May 20
Loving this @GIGABYTEUSA GB10 for local LLM work.
Quality is matching what I’m used to on Perplexity/Claude and the speed is great so far!
May 20
Not sure I’m the exact fit but, I’ve been deploying Hermes into my own businesses and clients businesses.
Multiple Hetzner servers running Hermes with a Gigabyte GB10 as the local model backend. Integrated messaging over various methods, Slack, Discord, custom UI and iMessage.
The agents manage CRM work, Database management, content, monitoring, more I am missing. 415 deployed skills, 11 enabled Hermes cron jobs, ops logging, robust working memory/RAG with a verified self-improvement loop at 50 completed runs.
1
1
1
176
Kyle Tusing retweeted
May 20
Not sure I’m the exact fit but, I’ve been deploying Hermes into my own businesses and clients businesses.
Multiple Hetzner servers running Hermes with a Gigabyte GB10 as the local model backend. Integrated messaging over various methods, Slack, Discord, custom UI and iMessage.
The agents manage CRM work, Database management, content, monitoring, more I am missing. 415 deployed skills, 11 enabled Hermes cron jobs, ops logging, robust working memory/RAG with a verified self-improvement loop at 50 completed runs.
3
1
22
1,777
May 18
Today’s project: turning a GIGABYTE AI TOP ATOM into a local LLM server for a client.
Their goal: stop renting other people’s GPUs and own the stack.
My job: wire it into an AI OS that runs their ops.
Stay tuned…
2
2
576
May 14
ES holds 7,483. NQ eyes 30,000.
Retail Sales printed. Tape is firm.
This week's board: NVDA, PLTR, 3 paid setups.
5 setups, 5 sectors, zero oil correlation.
Full playbook entries, stops, targets
Live now 🔗⬇️
#Trading #StockMarket #NVDA #ES #NQ #Futures #PLTR #SwingTrading
1
58