
Legal-trained entrepreneur. COO @NutriStyle: the nutrition intelligence platform for people who manage food and health on behalf of someone else.
Seattle
Joined March 2007
- Tweets17.1K
- Following7.5K
- Followers2.6K
- Likes49K
Lee Brillhart retweeted
I LAUNCHED A GROK BOT TERMINAL OVERNIGHT, GAVE IT $44.82 AND STOPPED ASKING AI WHAT IT WOULD DO. BY MORNING IT HAD $11,643.21 AND SIX AGENTS LOGGING EVERY TRADE
I spent a year asking agents what they'd trade and watching the chat scroll. Last weekend I built the thing that actually trades, in Grok Bot, with no code I touched by hand.
The six agents share one screen, each one job:
> scanner reads new token pairs and volume spikes
> rug check filters suspicious tokens before anything executes
> sizer sets position from account equity, not a fixed ticket
> executor opens and closes with slippage tracking
> logger writes the reason behind every trade
> equity curve updates on every close
I went to bed on $44.82 and left the laptop open on the dashboard. By morning the balance read $11,643.21. Every trade on the activity feed had a reason next to it and a line in the log.
That's the shift I didn't see coming. Not that an agent made money overnight. That I stopped being the one asking "would you long this?" and started being the one reading the log of what already happened.
Starting balance: $44.82
Current balance: $11,643.21
Grok Bot built the terminal, the agent architecture and the dashboard. I described what I wanted and the thing went live.
The full build is in the article below ↓
The whole build is in the post below ↓
Comment " Grok_Bot "
2️⃣ Like and Repost
3️⃣ Follow me @Nexa_Tech_Ai
I'll DM you the complete setup.
Family caregivers are doing clinical work without clinical tools.
Denise Brown just published data from 590 of them. On average they carry 34.7 of 53 care responsibilities across 8.3 of 9 caregiving domains. They put in 61.4 hours a week and have been doing it for 9.4 years.
11.4% reported 168 hours a week. That is every hour there is.
At $55 an hour, the average comes to $172,718 a year of work nobody pays for.
A professional doing that job would have training, protocols, software and a team. Most caregivers are working it out at the kitchen table.
2
2
87
Currently watching Alabama v Texas A&M on an alternative ESPN channel with no play by play announcers or analysts. Only commentary is what fans in the stadium hear. Cannot overstate how enjoyable this is.
97
Lee Brillhart retweeted
I lost my job yesterday.
Rent was due.
No backup plan.
Then I remembered I still had Claude.
Asked it:
“Analyze every top Polymarket wallet from the last 90 days and build me something”
$25 → $4,237 in one night.
It scanned 10,000 wallets.
Cross-referenced win rates, sizing, timing.
Found 7 traders whose edge wasn’t luck.
Then built an autonomous agent.
Not a script.
Not an if-then bot.
An agent that reads live news,
maps it to markets,
detects mispricing,
and exploits arbitrage across outcomes.
Sizes every position using Kelly.
I deployed it at 11:47PM.
Closed the laptop.
Woke up to:
$25 → $4,237
94 trades while I slept.
No input.
No hesitation.
No second-guessing.
That’s the game.
Information asymmetry at machine speed.
Wall Street pays millions for this.
I pay $20/month.
You only need Claude + laptop + 1 hour/day.
Giving This Free for 24 hours. To get it:
1. Comment the word 'AutoPilot'
2. Like and Retweet this post
3. Follow me @tec_marco10 (so i can DM you)
SF Tech Week starts today, and I have quite a busy schedule ahead of me.
Most Tech Week events end up in crowded conference rooms with generic small talk.
I am spending the week at private tables with founders building at the frontier and the investors backing them.
Here is where I will be:
Oct 6, 6pm: The Al Founders Table. 20 Al founders for high-context conversations about building at the frontier.
Oct 7, 8pm: Poker After Dark. Poker mixer with founders, operators, and investors.
Oct 8: VC x Founder Match. Funded founders meet Tier 1 investors on a rooftop, with everyone matched before arriving.
Oct 8, 8pm: Secret Soirée at HFO. An evening at The Chateau with oysters, live jazz, and a bit of magic.
RSVP links are in the comments below.
Most teams scaling voice AI are overpaying on inference by 40% and do not even realize it.
They pick whichever default pipeline looks easiest and string together a high-latency LLM with an expensive TTS provider.
Here is what I am seeing across deployments:
- A dedicated voice stack paired with a smaller model will outperform a frontier model on both speed and cost for real-time conversation.
- Self-hosting inference or swapping your STT provider can cut spend significantly without hurting call quality.
- The default setup is almost never the cheapest or the fastest.
If you are spending $10k+ a month on voice AI infrastructure and want a second opinion on your stack, DM me.
Tell me what models and providers you are currently running, and I will point you toward the teams that can cut your spend in half.








